Emerging hierarchies in dynamically adapting webs

NASA Astrophysics Data System (ADS)

Katifori, Eleni; Graewer, Johannes; Magnasco, Marcelo; Modes, Carl

Transport networks play a key role across four realms of eukaryotic life: slime molds, fungi, plants, and animals. In addition to the developmental algorithms that build them, many also employ adaptive strategies to respond to stimuli, damage, and other environmental changes. We model these adapting network architectures using a generic dynamical system on weighted graphs and find in simulation that these networks ultimately develop a hierarchical organization of the final weighted architecture accompanied by the formation of a system-spanning backbone. We quantify the hierarchical organization of the networks by developing an algorithm that decomposes the architecture to multiple scales and analyzes how the organization in each scale relates to that of the scale above and below it. The methodologies developed in this work are applicable to a wide range of systems including the slime mold physarum polycephalum, human microvasculature, and force chains in granular media.

Efficient self-organizing multilayer neural network for nonlinear system modeling.

PubMed

Han, Hong-Gui; Wang, Li-Dan; Qiao, Jun-Fei

2013-07-01

It has been shown extensively that the dynamic behaviors of a neural system are strongly influenced by the network architecture and learning process. To establish an artificial neural network (ANN) with self-organizing architecture and suitable learning algorithm for nonlinear system modeling, an automatic axon-neural network (AANN) is investigated in the following respects. First, the network architecture is constructed automatically to change both the number of hidden neurons and topologies of the neural network during the training process. The approach introduced in adaptive connecting-and-pruning algorithm (ACP) is a type of mixed mode operation, which is equivalent to pruning or adding the connecting of the neurons, as well as inserting some required neurons directly. Secondly, the weights are adjusted, using a feedforward computation (FC) to obtain the information for the gradient during learning computation. Unlike most of the previous studies, AANN is able to self-organize the architecture and weights, and to improve the network performances. Also, the proposed AANN has been tested on a number of benchmark problems, ranging from nonlinear function approximating to nonlinear systems modeling. The experimental results show that AANN can have better performances than that of some existing neural networks. Crown Copyright © 2013. Published by Elsevier Ltd. All rights reserved.

CHARACTERIZATION OF THE COMPLETE FIBER NETWORK TOPOLOGY OF PLANAR FIBROUS TISSUES AND SCAFFOLDS

PubMed Central

D'Amore, Antonio; Stella, John A.; Wagner, William R.; Sacks, Michael S.

2010-01-01

Understanding how engineered tissue scaffold architecture affects cell morphology, metabolism, phenotypic expression, as well as predicting material mechanical behavior have recently received increased attention. In the present study, an image-based analysis approach that provides an automated tool to characterize engineered tissue fiber network topology is presented. Micro-architectural features that fully defined fiber network topology were detected and quantified, which include fiber orientation, connectivity, intersection spatial density, and diameter. Algorithm performance was tested using scanning electron microscopy (SEM) images of electrospun poly(ester urethane)urea (ES-PEUU) scaffolds. SEM images of rabbit mesenchymal stem cell (MSC) seeded collagen gel scaffolds and decellularized rat carotid arteries were also analyzed to further evaluate the ability of the algorithm to capture fiber network morphology regardless of scaffold type and the evaluated size scale. The image analysis procedure was validated qualitatively and quantitatively, comparing fiber network topology manually detected by human operators (n=5) with that automatically detected by the algorithm. Correlation values between manual detected and algorithm detected results for the fiber angle distribution and for the fiber connectivity distribution were 0.86 and 0.93 respectively. Algorithm detected fiber intersections and fiber diameter values were comparable (within the mean ± standard deviation) with those detected by human operators. This automated approach identifies and quantifies fiber network morphology as demonstrated for three relevant scaffold types and provides a means to: (1) guarantee objectivity, (2) significantly reduce analysis time, and (3) potentiate broader analysis of scaffold architecture effects on cell behavior and tissue development both in vitro and in vivo. PMID:20398930

Loops in hierarchical channel networks

NASA Astrophysics Data System (ADS)

Katifori, Eleni; Magnasco, Marcelo

2012-02-01

Nature provides us with many examples of planar distribution and structural networks having dense sets of closed loops. An archetype of this form of network organization is the vasculature of dicotyledonous leaves, which showcases a hierarchically-nested architecture. Although a number of methods have been proposed to measure aspects of the structure of such networks, a robust metric to quantify their hierarchical organization is still lacking. We present an algorithmic framework that allows mapping loopy networks to binary trees, preserving in the connectivity of the trees the architecture of the original graph. We apply this framework to investigate computer generated and natural graphs extracted from digitized images of dicotyledonous leaves and animal vasculature. We calculate various metrics on the corresponding trees and discuss the relationship of these quantities to the architectural organization of the original graphs. This algorithmic framework decouples the geometric information from the metric topology (connectivity and edge weight) and it ultimately allows us to perform a quantitative statistical comparison between predictions of theoretical models and naturally occurring loopy graphs.

Biological engineering applications of feedforward neural networks designed and parameterized by genetic algorithms.

PubMed

Ferentinos, Konstantinos P

2005-09-01

Two neural network (NN) applications in the field of biological engineering are developed, designed and parameterized by an evolutionary method based on the evolutionary process of genetic algorithms. The developed systems are a fault detection NN model and a predictive modeling NN system. An indirect or 'weak specification' representation was used for the encoding of NN topologies and training parameters into genes of the genetic algorithm (GA). Some a priori knowledge of the demands in network topology for specific application cases is required by this approach, so that the infinite search space of the problem is limited to some reasonable degree. Both one-hidden-layer and two-hidden-layer network architectures were explored by the GA. Except for the network architecture, each gene of the GA also encoded the type of activation functions in both hidden and output nodes of the NN and the type of minimization algorithm that was used by the backpropagation algorithm for the training of the NN. Both models achieved satisfactory performance, while the GA system proved to be a powerful tool that can successfully replace the problematic trial-and-error approach that is usually used for these tasks.

DANoC: An Efficient Algorithm and Hardware Codesign of Deep Neural Networks on Chip.

PubMed

Zhou, Xichuan; Li, Shengli; Tang, Fang; Hu, Shengdong; Lin, Zhi; Zhang, Lei

2017-07-18

Deep neural networks (NNs) are the state-of-the-art models for understanding the content of images and videos. However, implementing deep NNs in embedded systems is a challenging task, e.g., a typical deep belief network could exhaust gigabytes of memory and result in bandwidth and computational bottlenecks. To address this challenge, this paper presents an algorithm and hardware codesign for efficient deep neural computation. A hardware-oriented deep learning algorithm, named the deep adaptive network, is proposed to explore the sparsity of neural connections. By adaptively removing the majority of neural connections and robustly representing the reserved connections using binary integers, the proposed algorithm could save up to 99.9% memory utility and computational resources without undermining classification accuracy. An efficient sparse-mapping-memory-based hardware architecture is proposed to fully take advantage of the algorithmic optimization. Different from traditional Von Neumann architecture, the deep-adaptive network on chip (DANoC) brings communication and computation in close proximity to avoid power-hungry parameter transfers between on-board memory and on-chip computational units. Experiments over different image classification benchmarks show that the DANoC system achieves competitively high accuracy and efficiency comparing with the state-of-the-art approaches.

Design development of a neural network-based telemetry monitor

NASA Technical Reports Server (NTRS)

Lembeck, Michael F.

1992-01-01

This paper identifies the requirements and describes an architectural framework for an artificial neural network-based system that is capable of fulfilling monitoring and control requirements of future aerospace missions. Incorporated into this framework are a newly developed training algorithm and the concept of cooperative network architectures. The feasibility of such an approach is demonstrated for its ability to identify faults in low frequency waveforms.

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.

ClusterViz: A Cytoscape APP for Cluster Analysis of Biological Network.

PubMed

Wang, Jianxin; Zhong, Jiancheng; Chen, Gang; Li, Min; Wu, Fang-xiang; Pan, Yi

2015-01-01

Cluster analysis of biological networks is one of the most important approaches for identifying functional modules and predicting protein functions. Furthermore, visualization of clustering results is crucial to uncover the structure of biological networks. In this paper, ClusterViz, an APP of Cytoscape 3 for cluster analysis and visualization, has been developed. In order to reduce complexity and enable extendibility for ClusterViz, we designed the architecture of ClusterViz based on the framework of Open Services Gateway Initiative. According to the architecture, the implementation of ClusterViz is partitioned into three modules including interface of ClusterViz, clustering algorithms and visualization and export. ClusterViz fascinates the comparison of the results of different algorithms to do further related analysis. Three commonly used clustering algorithms, FAG-EC, EAGLE and MCODE, are included in the current version. Due to adopting the abstract interface of algorithms in module of the clustering algorithms, more clustering algorithms can be included for the future use. To illustrate usability of ClusterViz, we provided three examples with detailed steps from the important scientific articles, which show that our tool has helped several research teams do their research work on the mechanism of the biological networks.

Smart photonic networks and computer security for image data

NASA Astrophysics Data System (ADS)

Campello, Jorge; Gill, John T.; Morf, Martin; Flynn, Michael J.

1998-02-01

Work reported here is part of a larger project on 'Smart Photonic Networks and Computer Security for Image Data', studying the interactions of coding and security, switching architecture simulations, and basic technologies. Coding and security: coding methods that are appropriate for data security in data fusion networks were investigated. These networks have several characteristics that distinguish them form other currently employed networks, such as Ethernet LANs or the Internet. The most significant characteristics are very high maximum data rates; predominance of image data; narrowcasting - transmission of data form one source to a designated set of receivers; data fusion - combining related data from several sources; simple sensor nodes with limited buffering. These characteristics affect both the lower level network design and the higher level coding methods.Data security encompasses privacy, integrity, reliability, and availability. Privacy, integrity, and reliability can be provided through encryption and coding for error detection and correction. Availability is primarily a network issue; network nodes must be protected against failure or routed around in the case of failure. One of the more promising techniques is the use of 'secret sharing'. We consider this method as a special case of our new space-time code diversity based algorithms for secure communication. These algorithms enable us to exploit parallelism and scalable multiplexing schemes to build photonic network architectures. A number of very high-speed switching and routing architectures and their relationships with very high performance processor architectures were studied. Indications are that routers for very high speed photonic networks can be designed using the very robust and distributed TCP/IP protocol, if suitable processor architecture support is available.

Protecting core networks with dual-homing: A study on enhanced network availability, resource efficiency, and energy-savings

NASA Astrophysics Data System (ADS)

Abeywickrama, Sandu; Furdek, Marija; Monti, Paolo; Wosinska, Lena; Wong, Elaine

2016-12-01

Core network survivability affects the reliability performance of telecommunication networks and remains one of the most important network design considerations. This paper critically examines the benefits arising from utilizing dual-homing in the optical access networks to provide resource-efficient protection against link and node failures in the optical core segment. Four novel, heuristic-based RWA algorithms that provide dedicated path protection in networks with dual-homing are proposed and studied. These algorithms protect against different failure scenarios (i.e. single link or node failures) and are implemented with different optimization objectives (i.e., minimization of wavelength usage and path length). Results obtained through simulations and comparison with baseline architectures indicate that exploiting dual-homed architecture in the access segment can bring significant improvements in terms of core network resource usage, connection availability, and power consumption.

Scalable service architecture for providing strong service guarantees

NASA Astrophysics Data System (ADS)

Christin, Nicolas; Liebeherr, Joerg

2002-07-01

For the past decade, a lot of Internet research has been devoted to providing different levels of service to applications. Initial proposals for service differentiation provided strong service guarantees, with strict bounds on delays, loss rates, and throughput, but required high overhead in terms of computational complexity and memory, both of which raise scalability concerns. Recently, the interest has shifted to service architectures with low overhead. However, these newer service architectures only provide weak service guarantees, which do not always address the needs of applications. In this paper, we describe a service architecture that supports strong service guarantees, can be implemented with low computational complexity, and only requires to maintain little state information. A key mechanism of the proposed service architecture is that it addresses scheduling and buffer management in a single algorithm. The presented architecture offers no solution for controlling the amount of traffic that enters the network. Instead, we plan on exploiting feedback mechanisms of TCP congestion control algorithms for the purpose of regulating the traffic entering the network.

Quantifying loopy network architectures.

PubMed

Katifori, Eleni; Magnasco, Marcelo O

2012-01-01

Biology presents many examples of planar distribution and structural networks having dense sets of closed loops. An archetype of this form of network organization is the vasculature of dicotyledonous leaves, which showcases a hierarchically-nested architecture containing closed loops at many different levels. Although a number of approaches have been proposed to measure aspects of the structure of such networks, a robust metric to quantify their hierarchical organization is still lacking. We present an algorithmic framework, the hierarchical loop decomposition, that allows mapping loopy networks to binary trees, preserving in the connectivity of the trees the architecture of the original graph. We apply this framework to investigate computer generated graphs, such as artificial models and optimal distribution networks, as well as natural graphs extracted from digitized images of dicotyledonous leaves and vasculature of rat cerebral neocortex. We calculate various metrics based on the asymmetry, the cumulative size distribution and the Strahler bifurcation ratios of the corresponding trees and discuss the relationship of these quantities to the architectural organization of the original graphs. This algorithmic framework decouples the geometric information (exact location of edges and nodes) from the metric topology (connectivity and edge weight) and it ultimately allows us to perform a quantitative statistical comparison between predictions of theoretical models and naturally occurring loopy graphs.

Path connectivity based spectral defragmentation in flexible bandwidth networks.

PubMed

Wang, Ying; Zhang, Jie; Zhao, Yongli; Zhang, Jiawei; Zhao, Jie; Wang, Xinbo; Gu, Wanyi

2013-01-28

Optical networks with flexible bandwidth provisioning have become a very promising networking architecture. It enables efficient resource utilization and supports heterogeneous bandwidth demands. In this paper, two novel spectrum defragmentation approaches, i.e. Maximum Path Connectivity (MPC) algorithm and Path Connectivity Triggering (PCT) algorithm, are proposed based on the notion of Path Connectivity, which is defined to represent the maximum variation of node switching ability along the path in flexible bandwidth networks. A cost-performance-ratio based profitability model is given to denote the prons and cons of spectrum defragmentation. We compare these two proposed algorithms with non-defragmentation algorithm in terms of blocking probability. Then we analyze the differences of defragmentation profitability between MPC and PCT algorithms.

An adaptable neural-network model for recursive nonlinear traffic prediction and modeling of MPEG video sources.

PubMed

Doulamis, A D; Doulamis, N D; Kollias, S D

2003-01-01

Multimedia services and especially digital video is expected to be the major traffic component transmitted over communication networks [such as internet protocol (IP)-based networks]. For this reason, traffic characterization and modeling of such services are required for an efficient network operation. The generated models can be used as traffic rate predictors, during the network operation phase (online traffic modeling), or as video generators for estimating the network resources, during the network design phase (offline traffic modeling). In this paper, an adaptable neural-network architecture is proposed covering both cases. The scheme is based on an efficient recursive weight estimation algorithm, which adapts the network response to current conditions. In particular, the algorithm updates the network weights so that 1) the network output, after the adaptation, is approximately equal to current bit rates (current traffic statistics) and 2) a minimal degradation over the obtained network knowledge is provided. It can be shown that the proposed adaptable neural-network architecture simulates a recursive nonlinear autoregressive model (RNAR) similar to the notation used in the linear case. The algorithm presents low computational complexity and high efficiency in tracking traffic rates in contrast to conventional retraining schemes. Furthermore, for the problem of offline traffic modeling, a novel correlation mechanism is proposed for capturing the burstness of the actual MPEG video traffic. The performance of the model is evaluated using several real-life MPEG coded video sources of long duration and compared with other linear/nonlinear techniques used for both cases. The results indicate that the proposed adaptable neural-network architecture presents better performance than other examined techniques.

Framewise phoneme classification with bidirectional LSTM and other neural network architectures.

PubMed

Graves, Alex; Schmidhuber, Jürgen

2005-01-01

In this paper, we present bidirectional Long Short Term Memory (LSTM) networks, and a modified, full gradient version of the LSTM learning algorithm. We evaluate Bidirectional LSTM (BLSTM) and several other network architectures on the benchmark task of framewise phoneme classification, using the TIMIT database. Our main findings are that bidirectional networks outperform unidirectional ones, and Long Short Term Memory (LSTM) is much faster and also more accurate than both standard Recurrent Neural Nets (RNNs) and time-windowed Multilayer Perceptrons (MLPs). Our results support the view that contextual information is crucial to speech processing, and suggest that BLSTM is an effective architecture with which to exploit it.

Network Coded Cooperative Communication in a Real-Time Wireless Hospital Sensor Network.

PubMed

Prakash, R; Balaji Ganesh, A; Sivabalan, Somu

2017-05-01

The paper presents a network coded cooperative communication (NC-CC) enabled wireless hospital sensor network architecture for monitoring health as well as postural activities of a patient. A wearable device, referred as a smartband is interfaced with pulse rate, body temperature sensors and an accelerometer along with wireless protocol services, such as Bluetooth and Radio-Frequency transceiver and Wi-Fi. The energy efficiency of wearable device is improved by embedding a linear acceleration based transmission duty cycling algorithm (NC-DRDC). The real-time demonstration is carried-out in a hospital environment to evaluate the performance characteristics, such as power spectral density, energy consumption, signal to noise ratio, packet delivery ratio and transmission offset. The resource sharing and energy efficiency features of network coding technique are improved by proposing an algorithm referred as network coding based dynamic retransmit/rebroadcast decision control (LA-TDC). From the experimental results, it is observed that the proposed LA-TDC algorithm reduces network traffic and end-to-end delay by an average of 27.8% and 21.6%, respectively than traditional network coded wireless transmission. The wireless architecture is deployed in a hospital environment and results are then successfully validated.

Dynamic optical resource allocation for mobile core networks with software defined elastic optical networking.

PubMed

Zhao, Yongli; Chen, Zhendong; Zhang, Jie; Wang, Xinbo

2016-07-25

Driven by the forthcoming of 5G mobile communications, the all-IP architecture of mobile core networks, i.e. evolved packet core (EPC) proposed by 3GPP, has been greatly challenged by the users' demands for higher data rate and more reliable end-to-end connection, as well as operators' demands for low operational cost. These challenges can be potentially met by software defined optical networking (SDON), which enables dynamic resource allocation according to the users' requirement. In this article, a novel network architecture for mobile core network is proposed based on SDON. A software defined network (SDN) controller is designed to realize the coordinated control over different entities in EPC networks. We analyze the requirement of EPC-lightpath (EPCL) in data plane and propose an optical switch load balancing (OSLB) algorithm for resource allocation in optical layer. The procedure of establishment and adjustment of EPCLs is demonstrated on a SDON-based EPC testbed with extended OpenFlow protocol. We also evaluate the OSLB algorithm through simulation in terms of bandwidth blocking ratio, traffic load distribution, and resource utilization ratio compared with link-based load balancing (LLB) and MinHops algorithms.

New Scheduling Algorithms for Agile All-Photonic Networks

NASA Astrophysics Data System (ADS)

Mehri, Mohammad Saleh; Ghaffarpour Rahbar, Akbar

2017-12-01

An optical overlaid star network is a class of agile all-photonic networks that consists of one or more core node(s) at the center of the star network and a number of edge nodes around the core node. In this architecture, a core node may use a scheduling algorithm for transmission of traffic through the network. A core node is responsible for scheduling optical packets that arrive from edge nodes and switching them toward their destinations. Nowadays, most edge nodes use virtual output queue (VOQ) architecture for buffering client packets to achieve high throughput. This paper presents two efficient scheduling algorithms called discretionary iterative matching (DIM) and adaptive DIM. These schedulers find maximum matching in a small number of iterations and provide high throughput and incur low delay. The number of arbiters in these schedulers and the number of messages exchanged between inputs and outputs of a core node are reduced. We show that DIM and adaptive DIM can provide better performance in comparison with iterative round-robin matching with SLIP (iSLIP). SLIP means the act of sliding for a short distance to select one of the requested connections based on the scheduling algorithm.

A Grey Wolf Optimizer for Modular Granular Neural Networks for Human Recognition

PubMed Central

Sánchez, Daniela; Melin, Patricia

2017-01-01

A grey wolf optimizer for modular neural network (MNN) with a granular approach is proposed. The proposed method performs optimal granulation of data and design of modular neural networks architectures to perform human recognition, and to prove its effectiveness benchmark databases of ear, iris, and face biometric measures are used to perform tests and comparisons against other works. The design of a modular granular neural network (MGNN) consists in finding optimal parameters of its architecture; these parameters are the number of subgranules, percentage of data for the training phase, learning algorithm, goal error, number of hidden layers, and their number of neurons. Nowadays, there is a great variety of approaches and new techniques within the evolutionary computing area, and these approaches and techniques have emerged to help find optimal solutions to problems or models and bioinspired algorithms are part of this area. In this work a grey wolf optimizer is proposed for the design of modular granular neural networks, and the results are compared against a genetic algorithm and a firefly algorithm in order to know which of these techniques provides better results when applied to human recognition. PMID:28894461

A Grey Wolf Optimizer for Modular Granular Neural Networks for Human Recognition.

PubMed

Sánchez, Daniela; Melin, Patricia; Castillo, Oscar

2017-01-01

A grey wolf optimizer for modular neural network (MNN) with a granular approach is proposed. The proposed method performs optimal granulation of data and design of modular neural networks architectures to perform human recognition, and to prove its effectiveness benchmark databases of ear, iris, and face biometric measures are used to perform tests and comparisons against other works. The design of a modular granular neural network (MGNN) consists in finding optimal parameters of its architecture; these parameters are the number of subgranules, percentage of data for the training phase, learning algorithm, goal error, number of hidden layers, and their number of neurons. Nowadays, there is a great variety of approaches and new techniques within the evolutionary computing area, and these approaches and techniques have emerged to help find optimal solutions to problems or models and bioinspired algorithms are part of this area. In this work a grey wolf optimizer is proposed for the design of modular granular neural networks, and the results are compared against a genetic algorithm and a firefly algorithm in order to know which of these techniques provides better results when applied to human recognition.

Performance evaluation of multi-stratum resources integrated resilience for software defined inter-data center interconnect.

PubMed

Yang, Hui; Zhang, Jie; Zhao, Yongli; Ji, Yuefeng; Wu, Jialin; Lin, Yi; Han, Jianrui; Lee, Young

2015-05-18

Inter-data center interconnect with IP over elastic optical network (EON) is a promising scenario to meet the high burstiness and high-bandwidth requirements of data center services. In our previous work, we implemented multi-stratum resources integration among IP networks, optical networks and application stratums resources that allows to accommodate data center services. In view of this, this study extends to consider the service resilience in case of edge optical node failure. We propose a novel multi-stratum resources integrated resilience (MSRIR) architecture for the services in software defined inter-data center interconnect based on IP over EON. A global resources integrated resilience (GRIR) algorithm is introduced based on the proposed architecture. The MSRIR can enable cross stratum optimization and provide resilience using the multiple stratums resources, and enhance the data center service resilience responsiveness to the dynamic end-to-end service demands. The overall feasibility and efficiency of the proposed architecture is experimentally verified on the control plane of our OpenFlow-based enhanced SDN (eSDN) testbed. The performance of GRIR algorithm under heavy traffic load scenario is also quantitatively evaluated based on MSRIR architecture in terms of path blocking probability, resilience latency and resource utilization, compared with other resilience algorithms.

Traffic engineering and regenerator placement in GMPLS networks with restoration

NASA Astrophysics Data System (ADS)

Yetginer, Emre; Karasan, Ezhan

2002-07-01

In this paper we study regenerator placement and traffic engineering of restorable paths in Generalized Multipro-tocol Label Switching (GMPLS) networks. Regenerators are necessary in optical networks due to transmission impairments. We study a network architecture where there are regenerators at selected nodes and we propose two heuristic algorithms for the regenerator placement problem. Performances of these algorithms in terms of required number of regenerators and computational complexity are evaluated. In this network architecture with sparse regeneration, offline computation of working and restoration paths is studied with bandwidth reservation and path rerouting as the restoration scheme. We study two approaches for selecting working and restoration paths from a set of candidate paths and formulate each method as an Integer Linear Programming (ILP) prob-lem. Traffic uncertainty model is developed in order to compare these methods based on their robustness with respect to changing traffic patterns. Traffic engineering methods are compared based on number of additional demands due to traffic uncertainty that can be carried. Regenerator placement algorithms are also evaluated from a traffic engineering point of view.

Next-Generation WDM Network Design and Routing

NASA Astrophysics Data System (ADS)

Tsang, Danny H. K.; Bensaou, Brahim

2003-08-01

Call for Papers The Editors of JON are soliciting papers on WDM Network Design and Routing. The aim in this focus issue is to publish original research on topics including - but not limited to - the following: - WDM network architectures and protocols - GMPLS network architectures - Wavelength converter placement in WDM networks - Routing and wavelength assignment (RWA) in WDM networks - Protection and restoration strategies and algorithms in WDM networks - Traffic grooming in WDM networks - Dynamic routing strategies and algorithms - Optical Burst Switching - Support of Multicast - Protection and restoration in WDM networks - Performance analysis and optimization in WDM networks Manuscript Submission To submit to this special issue, follow the normal procedure for submission to JON, indicating "WDM Network Design" in the "Comments" field of the online submission form. For all other questions relating to this focus issue, please send an e-mail to jon@osa.org, subject line "WDM Network Design." Additional information can be found on the JON website: http://www.osa-jon.org/submission/. Schedule Paper Submission Deadline: November 1, 2003 Notification to Authors: January 15, 2004 Final Manuscripts to Publisher: February 15, 2004 Publication of Focus Issue: February/March 2004

Next-Generation WDM Network Design and Routing

NASA Astrophysics Data System (ADS)

Tsang, Danny H. K.; Bensaou, Brahim

2003-10-01

Call for Papers The Editors of JON are soliciting papers on WDM Network Design and Routing. The aim in this focus issue is to publish original research on topics including - but not limited to - the following: - WDM network architectures and protocols - GMPLS network architectures - Wavelength converter placement in WDM networks - Routing and wavelength assignment (RWA) in WDM networks - Protection and restoration strategies and algorithms in WDM networks - Traffic grooming in WDM networks - Dynamic routing strategies and algorithms - Optical burst switching - Support of multicast - Protection and restoration in WDM networks - Performance analysis and optimization in WDM networks Manuscript Submission To submit to this special issue, follow the normal procedure for submission to JON, indicating "WDM Network Design" in the "Comments" field of the online submission form. For all other questions relating to this focus issue, please send an e-mail to jon@osa.org, subject line "WDM Network Design." Additional information can be found on the JON website: http://www.osa-jon.org/submission/. Schedule - Paper Submission Deadline: November 1, 2003 - Notification to Authors: January 15, 2004 - Final Manuscripts to Publisher: February 15, 2004 - Publication of Focus Issue: February/March 2004

Next-Generation WDM Network Design and Routing

NASA Astrophysics Data System (ADS)

Tsang, Danny H. K.; Bensaou, Brahim

2003-09-01

Call for Papers The Editors of JON are soliciting papers on WDM Network Design and Routing. The aim in this focus issue is to publish original research on topics including - but not limited to - the following: - WDM network architectures and protocols - GMPLS network architectures - Wavelength converter placement in WDM networks - Routing and wavelength assignment (RWA) in WDM networks - Protection and restoration strategies and algorithms in WDM networks - Traffic grooming in WDM networks - Dynamic routing strategies and algorithms - Optical burst switching - Support of multicast - Protection and restoration in WDM networks - Performance analysis and optimization in WDM networks Manuscript Submission To submit to this special issue, follow the normal procedure for submission to JON, indicating "WDM Network Design" in the "Comments" field of the online submission form. For all other questions relating to this focus issue, please send an e-mail to jon@osa.org, subject line "WDM Network Design." Additional information can be found on the JON website: http://www.osa-jon.org/submission/. Schedule - Paper Submission Deadline: November 1, 2003 - Notification to Authors: January 15, 2004 - Final Manuscripts to Publisher: February 15, 2004 - Publication of Focus Issue: February/March 2004

Multiprocessor architecture: Synthesis and evaluation

NASA Technical Reports Server (NTRS)

Standley, Hilda M.

1990-01-01

Multiprocessor computed architecture evaluation for structural computations is the focus of the research effort described. Results obtained are expected to lead to more efficient use of existing architectures and to suggest designs for new, application specific, architectures. The brief descriptions given outline a number of related efforts directed toward this purpose. The difficulty is analyzing an existing architecture or in designing a new computer architecture lies in the fact that the performance of a particular architecture, within the context of a given application, is determined by a number of factors. These include, but are not limited to, the efficiency of the computation algorithm, the programming language and support environment, the quality of the program written in the programming language, the multiplicity of the processing elements, the characteristics of the individual processing elements, the interconnection network connecting processors and non-local memories, and the shared memory organization covering the spectrum from no shared memory (all local memory) to one global access memory. These performance determiners may be loosely classified as being software or hardware related. This distinction is not clear or even appropriate in many cases. The effect of the choice of algorithm is ignored by assuming that the algorithm is specified as given. Effort directed toward the removal of the effect of the programming language and program resulted in the design of a high-level parallel programming language. Two characteristics of the fundamental structure of the architecture (memory organization and interconnection network) are examined.

Neural Networks and other Techniques for Fault Identification and Isolation of Aircraft Systems

NASA Technical Reports Server (NTRS)

Innocenti, M.; Napolitano, M.

2003-01-01

Fault identification, isolation, and accomodation have become critical issues in the overall performance of advanced aircraft systems. Neural Networks have shown to be a very attractive alternative to classic adaptation methods for identification and control of non-linear dynamic systems. The purpose of this paper is to show the improvements in neural network applications achievable through the use of learning algorithms more efficient than the classic Back-Propagation, and through the implementation of the neural schemes in parallel hardware. The results of the analysis of a scheme for Sensor Failure, Detection, Identification and Accommodation (SFDIA) using experimental flight data of a research aircraft model are presented. Conventional approaches to the problem are based on observers and Kalman Filters while more recent methods are based on neural approximators. The work described in this paper is based on the use of neural networks (NNs) as on-line learning non-linear approximators. The performances of two different neural architectures were compared. The first architecture is based on a Multi Layer Perceptron (MLP) NN trained with the Extended Back Propagation algorithm (EBPA). The second architecture is based on a Radial Basis Function (RBF) NN trained with the Extended-MRAN (EMRAN) algorithms. In addition, alternative methods for communications links fault detection and accomodation are presented, relative to multiple unmanned aircraft applications.

Program Helps Simulate Neural Networks

NASA Technical Reports Server (NTRS)

Villarreal, James; Mcintire, Gary

1993-01-01

Neural Network Environment on Transputer System (NNETS) computer program provides users high degree of flexibility in creating and manipulating wide variety of neural-network topologies at processing speeds not found in conventional computing environments. Supports back-propagation and back-propagation-related algorithms. Back-propagation algorithm used is implementation of Rumelhart's generalized delta rule. NNETS developed on INMOS Transputer(R). Predefines back-propagation network, Jordan network, and reinforcement network to assist users in learning and defining own networks. Also enables users to configure other neural-network paradigms from NNETS basic architecture. Small portion of software written in OCCAM(R) language.

Architecutres, Models, Algorithms, and Software Tools for Configurable Computing

DTIC Science & Technology

2000-03-06

and J.G. Nash. The gated interconnection network for dynamic programming. Plenum, 1988 . [18] Ju wook Jang, Heonchul Park, and Viktor K. Prasanna. A ...Sep. 1997. [2] C. Ebeling, D. C. Cronquist , P. Franklin and C. Fisher, "RaPiD - A configurable computing architecture for compute-intensive...ABSTRACT (Maximum 200 words) The Models, Algorithms, and Architectures for Reconfigurable Computing (MAARC) project developed a sound framework for

Superior Generalization Capability of Hardware-Learing Algorithm Developed for Self-Learning Neuron-MOS Neural Networks

NASA Astrophysics Data System (ADS)

Kondo, Shuhei; Shibata, Tadashi; Ohmi, Tadahiro

1995-02-01

We have investigated the learning performance of the hardware backpropagation (HBP) algorithm, a hardware-oriented learning algorithm developed for the self-learning architecture of neural networks constructed using neuron MOS (metal-oxide-semiconductor) transistors. The solution to finding a mirror symmetry axis in a 4×4 binary pixel array was tested by computer simulation based on the HBP algorithm. Despite the inherent restrictions imposed on the hardware-learning algorithm, HBP exhibits equivalent learning performance to that of the original backpropagation (BP) algorithm when all the pertinent parameters are optimized. Very importantly, we have found that HBP has a superior generalization capability over BP; namely, HBP exhibits higher performance in solving problems that the network has not yet learnt.

Sub-microradian pointing for deep space optical telecommunications network

NASA Technical Reports Server (NTRS)

Ortiz, G.; Lee, S.; Alexander, J.

2001-01-01

This presentation will cover innovative hardware, algorithms, architectures, techniques and recent laboratory results that are applicable to all deep space optical communication links, such as the Mars Telecommunication Network to future interstellar missions.

Stable architectures for deep neural networks

NASA Astrophysics Data System (ADS)

Haber, Eldad; Ruthotto, Lars

2018-01-01

Deep neural networks have become invaluable tools for supervised machine learning, e.g. classification of text or images. While often offering superior results over traditional techniques and successfully expressing complicated patterns in data, deep architectures are known to be challenging to design and train such that they generalize well to new data. Critical issues with deep architectures are numerical instabilities in derivative-based learning algorithms commonly called exploding or vanishing gradients. In this paper, we propose new forward propagation techniques inspired by systems of ordinary differential equations (ODE) that overcome this challenge and lead to well-posed learning problems for arbitrarily deep networks. The backbone of our approach is our interpretation of deep learning as a parameter estimation problem of nonlinear dynamical systems. Given this formulation, we analyze stability and well-posedness of deep learning and use this new understanding to develop new network architectures. We relate the exploding and vanishing gradient phenomenon to the stability of the discrete ODE and present several strategies for stabilizing deep learning for very deep networks. While our new architectures restrict the solution space, several numerical experiments show their competitiveness with state-of-the-art networks.

Parallel protein secondary structure prediction based on neural networks.

PubMed

Zhong, Wei; Altun, Gulsah; Tian, Xinmin; Harrison, Robert; Tai, Phang C; Pan, Yi

2004-01-01

Protein secondary structure prediction has a fundamental influence on today's bioinformatics research. In this work, binary and tertiary classifiers of protein secondary structure prediction are implemented on Denoeux belief neural network (DBNN) architecture. Hydrophobicity matrix, orthogonal matrix, BLOSUM62 and PSSM (position specific scoring matrix) are experimented separately as the encoding schemes for DBNN. The experimental results contribute to the design of new encoding schemes. New binary classifier for Helix versus not Helix ( approximately H) for DBNN produces prediction accuracy of 87% when PSSM is used for the input profile. The performance of DBNN binary classifier is comparable to other best prediction methods. The good test results for binary classifiers open a new approach for protein structure prediction with neural networks. Due to the time consuming task of training the neural networks, Pthread and OpenMP are employed to parallelize DBNN in the hyperthreading enabled Intel architecture. Speedup for 16 Pthreads is 4.9 and speedup for 16 OpenMP threads is 4 in the 4 processors shared memory architecture. Both speedup performance of OpenMP and Pthread is superior to that of other research. With the new parallel training algorithm, thousands of amino acids can be processed in reasonable amount of time. Our research also shows that hyperthreading technology for Intel architecture is efficient for parallel biological algorithms.

Dynamic virtual optical network embedding in spectral and spatial domains over elastic optical networks with multicore fibers

NASA Astrophysics Data System (ADS)

Zhu, Ruijie; Zhao, Yongli; Yang, Hui; Tan, Yuanlong; Chen, Haoran; Zhang, Jie; Jue, Jason P.

2016-08-01

Network virtualization can eradicate the ossification of the infrastructure and stimulate innovation of new network architectures and applications. Elastic optical networks (EONs) are ideal substrate networks for provisioning flexible virtual optical network (VON) services. However, as network traffic continues to increase exponentially, the capacity of EONs will reach the physical limitation soon. To further increase network flexibility and capacity, the concept of EONs is extended into the spatial domain. How to map the VON onto substrate networks by thoroughly using the spectral and spatial resources is extremely important. This process is called VON embedding (VONE).Considering the two kinds of resources at the same time during the embedding process, we propose two VONE algorithms, the adjacent link embedding algorithm (ALEA) and the remote link embedding algorithm (RLEA). First, we introduce a model to solve the VONE problem. Then we design the embedding ability measurement of network elements. Based on the network elements' embedding ability, two VONE algorithms were proposed. Simulation results show that the proposed VONE algorithms could achieve better performance than the baseline algorithm in terms of blocking probability and revenue-to-cost ratio.

Connectivity: Performance Portable Algorithms for graph connectivity v. 0.1

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

Slota, George; Rajamanickam, Sivasankaran; Madduri, Kamesh

Graphs occur in several places in real world from road networks, social networks and scientific simulations. Connectivity is a graph analysis software to graph connectivity in modern architectures like multicore CPUs, Xeon Phi and GPUs.

Parallel architectures for iterative methods on adaptive, block structured grids

NASA Technical Reports Server (NTRS)

Gannon, D.; Vanrosendale, J.

1983-01-01

A parallel computer architecture well suited to the solution of partial differential equations in complicated geometries is proposed. Algorithms for partial differential equations contain a great deal of parallelism. But this parallelism can be difficult to exploit, particularly on complex problems. One approach to extraction of this parallelism is the use of special purpose architectures tuned to a given problem class. The architecture proposed here is tuned to boundary value problems on complex domains. An adaptive elliptic algorithm which maps effectively onto the proposed architecture is considered in detail. Two levels of parallelism are exploited by the proposed architecture. First, by making use of the freedom one has in grid generation, one can construct grids which are locally regular, permitting a one to one mapping of grids to systolic style processor arrays, at least over small regions. All local parallelism can be extracted by this approach. Second, though there may be a regular global structure to the grids constructed, there will be parallelism at this level. One approach to finding and exploiting this parallelism is to use an architecture having a number of processor clusters connected by a switching network. The use of such a network creates a highly flexible architecture which automatically configures to the problem being solved.

Programmable bandwidth management in software-defined EPON architecture

NASA Astrophysics Data System (ADS)

Li, Chengjun; Guo, Wei; Wang, Wei; Hu, Weisheng; Xia, Ming

2016-07-01

This paper proposes a software-defined EPON architecture which replaces the hardware-implemented DBA module with reprogrammable DBA module. The DBA module allows pluggable bandwidth allocation algorithms among multiple ONUs adaptive to traffic profiles and network states. We also introduce a bandwidth management scheme executed at the controller to manage the customized DBA algorithms for all date queues of ONUs. Our performance investigation verifies the effectiveness of this new EPON architecture, and numerical results show that software-defined EPONs can achieve less traffic delay and provide better support to service differentiation in comparison with traditional EPONs.

Brain-Inspired Constructive Learning Algorithms with Evolutionally Additive Nonlinear Neurons

NASA Astrophysics Data System (ADS)

Fang, Le-Heng; Lin, Wei; Luo, Qiang

In this article, inspired partially by the physiological evidence of brain’s growth and development, we developed a new type of constructive learning algorithm with evolutionally additive nonlinear neurons. The new algorithms have remarkable ability in effective regression and accurate classification. In particular, the algorithms are able to sustain a certain reduction of the loss function when the dynamics of the trained network are bogged down in the vicinity of the local minima. The algorithm augments the neural network by adding only a few connections as well as neurons whose activation functions are nonlinear, nonmonotonic, and self-adapted to the dynamics of the loss functions. Indeed, we analytically demonstrate the reduction dynamics of the algorithm for different problems, and further modify the algorithms so as to obtain an improved generalization capability for the augmented neural networks. Finally, through comparing with the classical algorithm and architecture for neural network construction, we show that our constructive learning algorithms as well as their modified versions have better performances, such as faster training speed and smaller network size, on several representative benchmark datasets including the MNIST dataset for handwriting digits.

An Efficient Implementation of Deep Convolutional Neural Networks for MRI Segmentation.

PubMed

Hoseini, Farnaz; Shahbahrami, Asadollah; Bayat, Peyman

2018-02-27

Image segmentation is one of the most common steps in digital image processing, classifying a digital image into different segments. The main goal of this paper is to segment brain tumors in magnetic resonance images (MRI) using deep learning. Tumors having different shapes, sizes, brightness and textures can appear anywhere in the brain. These complexities are the reasons to choose a high-capacity Deep Convolutional Neural Network (DCNN) containing more than one layer. The proposed DCNN contains two parts: architecture and learning algorithms. The architecture and the learning algorithms are used to design a network model and to optimize parameters for the network training phase, respectively. The architecture contains five convolutional layers, all using 3 × 3 kernels, and one fully connected layer. Due to the advantage of using small kernels with fold, it allows making the effect of larger kernels with smaller number of parameters and fewer computations. Using the Dice Similarity Coefficient metric, we report accuracy results on the BRATS 2016, brain tumor segmentation challenge dataset, for the complete, core, and enhancing regions as 0.90, 0.85, and 0.84 respectively. The learning algorithm includes the task-level parallelism. All the pixels of an MR image are classified using a patch-based approach for segmentation. We attain a good performance and the experimental results show that the proposed DCNN increases the segmentation accuracy compared to previous techniques.

A space-time neural network

NASA Technical Reports Server (NTRS)

Villarreal, James A.; Shelton, Robert O.

1991-01-01

Introduced here is a novel technique which adds the dimension of time to the well known back propagation neural network algorithm. Cited here are several reasons why the inclusion of automated spatial and temporal associations are crucial to effective systems modeling. An overview of other works which also model spatiotemporal dynamics is furnished. A detailed description is given of the processes necessary to implement the space-time network algorithm. Several demonstrations that illustrate the capabilities and performance of this new architecture are given.

Wireless Sensor Networks for Ambient Assisted Living

PubMed Central

Aquino-Santos, Raúl; Martinez-Castro, Diego; Edwards-Block, Arthur; Murillo-Piedrahita, Andrés Felipe

2013-01-01

This paper introduces wireless sensor networks for Ambient Assisted Living as a proof of concept. Our workgroup has developed an arrhythmia detection algorithm that we evaluate in a closed space using a wireless sensor network to relay the information collected to where the information can be registered, monitored and analyzed to support medical decisions by healthcare providers. The prototype we developed is then evaluated using the TelosB platform. The proposed architecture considers very specific restrictions regarding the use of wireless sensor networks in clinical situations. The seamless integration of the system architecture enables both mobile node and network configuration, thus providing the versatile and robust characteristics necessary for real-time applications in medical situations. Likewise, this system architecture efficiently permits the different components of our proposed platform to interact efficiently within the parameters of this study. PMID:24351665

Ultrascalable petaflop parallel supercomputer

DOEpatents

Blumrich, Matthias A [Ridgefield, CT; Chen, Dong [Croton On Hudson, NY; Chiu, George [Cross River, NY; Cipolla, Thomas M [Katonah, NY; Coteus, Paul W [Yorktown Heights, NY; Gara, Alan G [Mount Kisco, NY; Giampapa, Mark E [Irvington, NY; Hall, Shawn [Pleasantville, NY; Haring, Rudolf A [Cortlandt Manor, NY; Heidelberger, Philip [Cortlandt Manor, NY; Kopcsay, Gerard V [Yorktown Heights, NY; Ohmacht, Martin [Yorktown Heights, NY; Salapura, Valentina [Chappaqua, NY; Sugavanam, Krishnan [Mahopac, NY; Takken, Todd [Brewster, NY

2010-07-20

A massively parallel supercomputer of petaOPS-scale includes node architectures based upon System-On-a-Chip technology, where each processing node comprises a single Application Specific Integrated Circuit (ASIC) having up to four processing elements. The ASIC nodes are interconnected by multiple independent networks that optimally maximize the throughput of packet communications between nodes with minimal latency. The multiple networks may include three high-speed networks for parallel algorithm message passing including a Torus, collective network, and a Global Asynchronous network that provides global barrier and notification functions. These multiple independent networks may be collaboratively or independently utilized according to the needs or phases of an algorithm for optimizing algorithm processing performance. The use of a DMA engine is provided to facilitate message passing among the nodes without the expenditure of processing resources at the node.

Energy-Efficient Transmissions for Remote Wireless Sensor Networks: An Integrated HAP/Satellite Architecture for Emergency Scenarios

PubMed Central

Dong, Feihong; Li, Hongjun; Gong, Xiangwu; Liu, Quan; Wang, Jingchao

2015-01-01

A typical application scenario of remote wireless sensor networks (WSNs) is identified as an emergency scenario. One of the greatest design challenges for communications in emergency scenarios is energy-efficient transmission, due to scarce electrical energy in large-scale natural and man-made disasters. Integrated high altitude platform (HAP)/satellite networks are expected to optimally meet emergency communication requirements. In this paper, a novel integrated HAP/satellite (IHS) architecture is proposed, and three segments of the architecture are investigated in detail. The concept of link-state advertisement (LSA) is designed in a slow flat Rician fading channel. The LSA is received and processed by the terminal to estimate the link state information, which can significantly reduce the energy consumption at the terminal end. Furthermore, the transmission power requirements of the HAPs and terminals are derived using the gradient descent and differential equation methods. The energy consumption is modeled at both the source and system level. An innovative and adaptive algorithm is given for the energy-efficient path selection. The simulation results validate the effectiveness of the proposed adaptive algorithm. It is shown that the proposed adaptive algorithm can significantly improve energy efficiency when combined with the LSA and the energy consumption estimation. PMID:26404292

Energy-Efficient Transmissions for Remote Wireless Sensor Networks: An Integrated HAP/Satellite Architecture for Emergency Scenarios.

PubMed

Dong, Feihong; Li, Hongjun; Gong, Xiangwu; Liu, Quan; Wang, Jingchao

2015-09-03

A typical application scenario of remote wireless sensor networks (WSNs) is identified as an emergency scenario. One of the greatest design challenges for communications in emergency scenarios is energy-efficient transmission, due to scarce electrical energy in large-scale natural and man-made disasters. Integrated high altitude platform (HAP)/satellite networks are expected to optimally meet emergency communication requirements. In this paper, a novel integrated HAP/satellite (IHS) architecture is proposed, and three segments of the architecture are investigated in detail. The concept of link-state advertisement (LSA) is designed in a slow flat Rician fading channel. The LSA is received and processed by the terminal to estimate the link state information, which can significantly reduce the energy consumption at the terminal end. Furthermore, the transmission power requirements of the HAPs and terminals are derived using the gradient descent and differential equation methods. The energy consumption is modeled at both the source and system level. An innovative and adaptive algorithm is given for the energy-efficient path selection. The simulation results validate the effectiveness of the proposed adaptive algorithm. It is shown that the proposed adaptive algorithm can significantly improve energy efficiency when combined with the LSA and the energy consumption estimation.

Using Hybrid Algorithm to Improve Intrusion Detection in Multi Layer Feed Forward Neural Networks

ERIC Educational Resources Information Center

Ray, Loye Lynn

2014-01-01

The need for detecting malicious behavior on a computer networks continued to be important to maintaining a safe and secure environment. The purpose of this study was to determine the relationship of multilayer feed forward neural network architecture to the ability of detecting abnormal behavior in networks. This involved building, training, and…

Special Issue on a Fault Tolerant Network on Chip Architecture

NASA Astrophysics Data System (ADS)

Janidarmian, Majid; Tinati, Melika; Khademzadeh, Ahmad; Ghavibazou, Maryam; Fekr, Atena Roshan

2010-06-01

In this paper a fast and efficient spare switch selection algorithm is presented in a reliable NoC architecture based on specific application mapped onto mesh topology called FERNA. Based on ring concept used in FERNA, this algorithm achieves best results equivalent to exhaustive algorithm with much less run time improving two parameters. Inputs of FERNA algorithm for response time of the system and extra communication cost minimization are derived from simulation of high transaction level using SystemC TLM and mathematical formulation, respectively. The results demonstrate that improvement of above mentioned parameters lead to advance whole system reliability that is analytically calculated. Mapping algorithm has been also investigated as an effective issue on extra bandwidth requirement and system reliability.

Streaming parallel GPU acceleration of large-scale filter-based spiking neural networks.

PubMed

Slażyński, Leszek; Bohte, Sander

2012-01-01

The arrival of graphics processing (GPU) cards suitable for massively parallel computing promises affordable large-scale neural network simulation previously only available at supercomputing facilities. While the raw numbers suggest that GPUs may outperform CPUs by at least an order of magnitude, the challenge is to develop fine-grained parallel algorithms to fully exploit the particulars of GPUs. Computation in a neural network is inherently parallel and thus a natural match for GPU architectures: given inputs, the internal state for each neuron can be updated in parallel. We show that for filter-based spiking neurons, like the Spike Response Model, the additive nature of membrane potential dynamics enables additional update parallelism. This also reduces the accumulation of numerical errors when using single precision computation, the native precision of GPUs. We further show that optimizing simulation algorithms and data structures to the GPU's architecture has a large pay-off: for example, matching iterative neural updating to the memory architecture of the GPU speeds up this simulation step by a factor of three to five. With such optimizations, we can simulate in better-than-realtime plausible spiking neural networks of up to 50 000 neurons, processing over 35 million spiking events per second.

Kanerva's sparse distributed memory: An associative memory algorithm well-suited to the Connection Machine

NASA Technical Reports Server (NTRS)

Rogers, David

1988-01-01

The advent of the Connection Machine profoundly changes the world of supercomputers. The highly nontraditional architecture makes possible the exploration of algorithms that were impractical for standard Von Neumann architectures. Sparse distributed memory (SDM) is an example of such an algorithm. Sparse distributed memory is a particularly simple and elegant formulation for an associative memory. The foundations for sparse distributed memory are described, and some simple examples of using the memory are presented. The relationship of sparse distributed memory to three important computational systems is shown: random-access memory, neural networks, and the cerebellum of the brain. Finally, the implementation of the algorithm for sparse distributed memory on the Connection Machine is discussed.

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.

Modular multiplication in GF(p) for public-key cryptography

NASA Astrophysics Data System (ADS)

Olszyna, Jakub

Modular multiplication forms the basis of modular exponentiation which is the core operation of the RSA cryptosystem. It is also present in many other cryptographic algorithms including those based on ECC and HECC. Hence, an efficient implementation of PKC relies on efficient implementation of modular multiplication. The paper presents a survey of most common algorithms for modular multiplication along with hardware architectures especially suitable for cryptographic applications in energy constrained environments. The motivation for studying low-power and areaefficient modular multiplication algorithms comes from enabling public-key security for ultra-low power devices that can perform under constrained environments like wireless sensor networks. Serial architectures for GF(p) are analyzed and presented. Finally proposed architectures are verified and compared according to the amount of power dissipated throughout the operation.

An epidemic model for biological data fusion in ad hoc sensor networks

NASA Astrophysics Data System (ADS)

Chang, K. C.; Kotari, Vikas

2009-05-01

Bio terrorism can be a very refined and a catastrophic approach of attacking a nation. This requires the development of a complete architecture dedicatedly designed for this purpose which includes but is not limited to Sensing/Detection, Tracking and Fusion, Communication, and others. In this paper we focus on one such architecture and evaluate its performance. Various sensors for this specific purpose have been studied. The accent has been on use of Distributed systems such as ad-hoc networks and on application of epidemic data fusion algorithms to better manage the bio threat data. The emphasis has been on understanding the performance characteristics of these algorithms under diversified real time scenarios which are implemented through extensive JAVA based simulations. Through comparative studies on communication and fusion the performance of channel filter algorithm for the purpose of biological sensor data fusion are validated.

A high performance parallel computing architecture for robust image features

NASA Astrophysics Data System (ADS)

Zhou, Renyan; Liu, Leibo; Wei, Shaojun

2014-03-01

A design of parallel architecture for image feature detection and description is proposed in this article. The major component of this architecture is a 2D cellular network composed of simple reprogrammable processors, enabling the Hessian Blob Detector and Haar Response Calculation, which are the most computing-intensive stage of the Speeded Up Robust Features (SURF) algorithm. Combining this 2D cellular network and dedicated hardware for SURF descriptors, this architecture achieves real-time image feature detection with minimal software in the host processor. A prototype FPGA implementation of the proposed architecture achieves 1318.9 GOPS general pixel processing @ 100 MHz clock and achieves up to 118 fps in VGA (640 × 480) image feature detection. The proposed architecture is stand-alone and scalable so it is easy to be migrated into VLSI implementation.

Introduction to a system for implementing neural net connections on SIMD architectures

NASA Technical Reports Server (NTRS)

Tomboulian, Sherryl

1988-01-01

Neural networks have attracted much interest recently, and using parallel architectures to simulate neural networks is a natural and necessary application. The SIMD model of parallel computation is chosen, because systems of this type can be built with large numbers of processing elements. However, such systems are not naturally suited to generalized communication. A method is proposed that allows an implementation of neural network connections on massively parallel SIMD architectures. The key to this system is an algorithm permitting the formation of arbitrary connections between the neurons. A feature is the ability to add new connections quickly. It also has error recovery ability and is robust over a variety of network topologies. Simulations of the general connection system, and its implementation on the Connection Machine, indicate that the time and space requirements are proportional to the product of the average number of connections per neuron and the diameter of the interconnection network.

Introduction to a system for implementing neural net connections on SIMD architectures

NASA Technical Reports Server (NTRS)

Tomboulian, Sherryl

1988-01-01

Neural networks have attracted much interest recently, and using parallel architectures to simulate neural networks is a natural and necessary application. The SIMD model of parallel computation is chosen, because systems of this type can be built with large numbers of processing elements. However, such systems are not naturally suited to generalized elements. A method is proposed that allows an implementation of neural network connections on massively parallel SIMD architectures. The key to this system is an algorithm permitting the formation of arbitrary connections between the neurons. A feature is the ability to add new connections quickly. It also has error recovery ability and is robust over a variety of network topologies. Simulations of the general connection system, and its implementation on the Connection Machine, indicate that the time and space requirements are proportional to the product of the average number of connections per neuron and the diameter of the interconnection network.

Brain Network Architecture and Global Intelligence in Children with Focal Epilepsy.

PubMed

Paldino, M J; Golriz, F; Chapieski, M L; Zhang, W; Chu, Z D

2017-02-01

The biologic basis for intelligence rests to a large degree on the capacity for efficient integration of information across the cerebral network. We aimed to measure the relationship between network architecture and intelligence in the pediatric, epileptic brain. Patients were retrospectively identified with the following: 1) focal epilepsy; 2) brain MR imaging at 3T, including resting-state functional MR imaging; and 3) full-scale intelligence quotient measured by a pediatric neuropsychologist. The cerebral cortex was parcellated into approximately 700 gray matter network "nodes." The strength of a connection between 2 nodes was defined by the correlation between their blood oxygen level-dependent time-series. We calculated the following topologic properties: clustering coefficient, transitivity, modularity, path length, and global efficiency. A machine learning algorithm was used to measure the independent contribution of each metric to the intelligence quotient after adjusting for all other metrics. Thirty patients met the criteria (4-18 years of age); 20 patients required anesthesia during MR imaging. After we accounted for age and sex, clustering coefficient and path length were independently associated with full-scale intelligence quotient. Neither motion parameters nor general anesthesia was an important variable with regard to accurate intelligence quotient prediction by the machine learning algorithm. A longer history of epilepsy was associated with shorter path lengths ( P = .008), consistent with reorganization of the network on the basis of seizures. Considering only patients receiving anesthesia during machine learning did not alter the patterns of network architecture contributing to global intelligence. These findings support the physiologic relevance of imaging-based metrics of network architecture in the pathologic, developing brain. © 2017 by American Journal of Neuroradiology.

An efficient fully unsupervised video object segmentation scheme using an adaptive neural-network classifier architecture.

PubMed

Doulamis, A; Doulamis, N; Ntalianis, K; Kollias, S

2003-01-01

In this paper, an unsupervised video object (VO) segmentation and tracking algorithm is proposed based on an adaptable neural-network architecture. The proposed scheme comprises: 1) a VO tracking module and 2) an initial VO estimation module. Object tracking is handled as a classification problem and implemented through an adaptive network classifier, which provides better results compared to conventional motion-based tracking algorithms. Network adaptation is accomplished through an efficient and cost effective weight updating algorithm, providing a minimum degradation of the previous network knowledge and taking into account the current content conditions. A retraining set is constructed and used for this purpose based on initial VO estimation results. Two different scenarios are investigated. The first concerns extraction of human entities in video conferencing applications, while the second exploits depth information to identify generic VOs in stereoscopic video sequences. Human face/ body detection based on Gaussian distributions is accomplished in the first scenario, while segmentation fusion is obtained using color and depth information in the second scenario. A decision mechanism is also incorporated to detect time instances for weight updating. Experimental results and comparisons indicate the good performance of the proposed scheme even in sequences with complicated content (object bending, occlusion).

Centralized and distributed control architectures under Foundation Fieldbus network.

PubMed

Persechini, Maria Auxiliadora Muanis; Jota, Fábio Gonçalves

2013-01-01

This paper aims at discussing possible automation and control system architectures based on fieldbus networks in which the controllers can be implemented either in a centralized or in a distributed form. An experimental setup is used to demonstrate some of the addressed issues. The control and automation architecture is composed of a supervisory system, a programmable logic controller and various other devices connected to a Foundation Fieldbus H1 network. The procedures used in the network configuration, in the process modelling and in the design and implementation of controllers are described. The specificities of each one of the considered logical organizations are also discussed. Finally, experimental results are analysed using an algorithm for the assessment of control loops to compare the performances between the centralized and the distributed implementations. Copyright © 2012 ISA. Published by Elsevier Ltd. All rights reserved.

Simple Algorithms for Distributed Leader Election in Anonymous Synchronous Rings and Complete Networks Inspired by Neural Development in Fruit Flies.

PubMed

Xu, Lei; Jeavons, Peter

2015-11-01

Leader election in anonymous rings and complete networks is a very practical problem in distributed computing. Previous algorithms for this problem are generally designed for a classical message passing model where complex messages are exchanged. However, the need to send and receive complex messages makes such algorithms less practical for some real applications. We present some simple synchronous algorithms for distributed leader election in anonymous rings and complete networks that are inspired by the development of the neural system of the fruit fly. Our leader election algorithms all assume that only one-bit messages are broadcast by nodes in the network and processors are only able to distinguish between silence and the arrival of one or more messages. These restrictions allow implementations to use a simpler message-passing architecture. Even with these harsh restrictions our algorithms are shown to achieve good time and message complexity both analytically and experimentally.

A Machine Learning Concept for DTN Routing

NASA Technical Reports Server (NTRS)

Dudukovich, Rachel; Hylton, Alan; Papachristou, Christos

2017-01-01

This paper discusses the concept and architecture of a machine learning based router for delay tolerant space networks. The techniques of reinforcement learning and Bayesian learning are used to supplement the routing decisions of the popular Contact Graph Routing algorithm. An introduction to the concepts of Contact Graph Routing, Q-routing and Naive Bayes classification are given. The development of an architecture for a cross-layer feedback framework for DTN (Delay-Tolerant Networking) protocols is discussed. Finally, initial simulation setup and results are given.

A Parallel Trade Study Architecture for Design Optimization of Complex Systems

NASA Technical Reports Server (NTRS)

Kim, Hongman; Mullins, James; Ragon, Scott; Soremekun, Grant; Sobieszczanski-Sobieski, Jaroslaw

2005-01-01

Design of a successful product requires evaluating many design alternatives in a limited design cycle time. This can be achieved through leveraging design space exploration tools and available computing resources on the network. This paper presents a parallel trade study architecture to integrate trade study clients and computing resources on a network using Web services. The parallel trade study solution is demonstrated to accelerate design of experiments, genetic algorithm optimization, and a cost as an independent variable (CAIV) study for a space system application.

Network simulations of optical illusions

NASA Astrophysics Data System (ADS)

Shinbrot, Troy; Lazo, Miguel Vivar; Siu, Theo

We examine a dynamical network model of visual processing that reproduces several aspects of a well-known optical illusion, including subtle dependencies on curvature and scale. The model uses a genetic algorithm to construct the percept of an image, and we show that this percept evolves dynamically so as to produce the illusions reported. We find that the perceived illusions are hardwired into the model architecture and we propose that this approach may serve as an archetype to distinguish behaviors that are due to nature (i.e. a fixed network architecture) from those subject to nurture (that can be plastically altered through learning).

Research on Localization Algorithms Based on Acoustic Communication for Underwater Sensor Networks

PubMed Central

Fan, Liying; Wu, Shan; Yan, Xueting

2017-01-01

The water source, as a significant body of the earth, with a high value, serves as a hot topic to study Underwater Sensor Networks (UWSNs). Various applications can be realized based on UWSNs. Our paper mainly concentrates on the localization algorithms based on the acoustic communication for UWSNs. An in-depth survey of localization algorithms is provided for UWSNs. We first introduce the acoustic communication, network architecture, and routing technique in UWSNs. The localization algorithms are classified into five aspects, namely, computation algorithm, spatial coverage, range measurement, the state of the nodes and communication between nodes that are different from all other survey papers. Moreover, we collect a lot of pioneering papers, and a comprehensive comparison is made. In addition, some challenges and open issues are raised in our paper. PMID:29301369

An adaptive transmission protocol for managing dynamic shared states in collaborative surgical simulation.

PubMed

Qin, J; Choi, K S; Ho, Simon S M; Heng, P A

2008-01-01

A force prediction algorithm is proposed to facilitate virtual-reality (VR) based collaborative surgical simulation by reducing the effect of network latencies. State regeneration is used to correct the estimated prediction. This algorithm is incorporated into an adaptive transmission protocol in which auxiliary features such as view synchronization and coupling control are equipped to ensure the system consistency. We implemented this protocol using multi-threaded technique on a cluster-based network architecture.

Multicast routing for wavelength-routed WDM networks with dynamic membership

NASA Astrophysics Data System (ADS)

Huang, Nen-Fu; Liu, Te-Lung; Wang, Yao-Tzung; Li, Bo

2000-09-01

Future broadband networks must support integrated services and offer flexible bandwidth usage. In our previous work, we explore the optical link control layer on the top of optical layer that enables the possibility of bandwidth on-demand service directly over wavelength division multiplexed (WDM) networks. Today, more and more applications and services such as video-conferencing software and Virtual LAN service require multicast support over the underlying networks. Currently, it is difficult to provide wavelength multicast over the optical switches without optical/electronic conversions although the conversion takes extra cost. In this paper, based on the proposed wavelength router architecture (equipped with ATM switches to offer O/E and E/O conversions when necessary), a dynamic multicast routing algorithm is proposed to furnish multicast services over WDM networks. The goal is to joint a new group member into the multicast tree so that the cost, including the link cost and the optical/electronic conversion cost, is kept as less as possible. The effectiveness of the proposed wavelength router architecture as well as the dynamic multicast algorithm is evaluated by simulation.

Architectural Implications for Spatial Object Association Algorithms*

PubMed Central

Kumar, Vijay S.; Kurc, Tahsin; Saltz, Joel; Abdulla, Ghaleb; Kohn, Scott R.; Matarazzo, Celeste

2013-01-01

Spatial object association, also referred to as crossmatch of spatial datasets, is the problem of identifying and comparing objects in two or more datasets based on their positions in a common spatial coordinate system. In this work, we evaluate two crossmatch algorithms that are used for astronomical sky surveys, on the following database system architecture configurations: (1) Netezza Performance Server®, a parallel database system with active disk style processing capabilities, (2) MySQL Cluster, a high-throughput network database system, and (3) a hybrid configuration consisting of a collection of independent database system instances with data replication support. Our evaluation provides insights about how architectural characteristics of these systems affect the performance of the spatial crossmatch algorithms. We conducted our study using real use-case scenarios borrowed from a large-scale astronomy application known as the Large Synoptic Survey Telescope (LSST). PMID:25692244

A large-scale photonic node architecture that utilizes interconnected OXC subsystems.

PubMed

Iwai, Yuto; Hasegawa, Hiroshi; Sato, Ken-ichi

2013-01-14

We propose a novel photonic node architecture that is composed of interconnected small-scale optical cross-connect subsystems. We also developed an efficient dynamic network control algorithm that complies with a restriction on the number of intra-node fibers used for subsystem interconnection. Numerical evaluations verify that the proposed architecture offers almost the same performance as the equivalent single large-scale cross-connect switch, while enabling substantial hardware scale reductions.

A grid layout algorithm for automatic drawing of biochemical networks.

PubMed

Li, Weijiang; Kurata, Hiroyuki

2005-05-01

Visualization is indispensable in the research of complex biochemical networks. Available graph layout algorithms are not adequate for satisfactorily drawing such networks. New methods are required to visualize automatically the topological architectures and facilitate the understanding of the functions of the networks. We propose a novel layout algorithm to draw complex biochemical networks. A network is modeled as a system of interacting nodes on squared grids. A discrete cost function between each node pair is designed based on the topological relation and the geometric positions of the two nodes. The layouts are produced by minimizing the total cost. We design a fast algorithm to minimize the discrete cost function, by which candidate layouts can be produced efficiently. A simulated annealing procedure is used to choose better candidates. Our algorithm demonstrates its ability to exhibit cluster structures clearly in relatively compact layout areas without any prior knowledge. We developed Windows software to implement the algorithm for CADLIVE. All materials can be freely downloaded from http://kurata21.bio.kyutech.ac.jp/grid/grid_layout.htm; http://www.cadlive.jp/ http://kurata21.bio.kyutech.ac.jp/grid/grid_layout.htm; http://www.cadlive.jp/

Structural self-assembly and avalanchelike dynamics in locally adaptive networks

NASA Astrophysics Data System (ADS)

Gräwer, Johannes; Modes, Carl D.; Magnasco, Marcelo O.; Katifori, Eleni

2015-07-01

Transport networks play a key role across four realms of eukaryotic life: slime molds, fungi, plants, and animals. In addition to the developmental algorithms that build them, many also employ adaptive strategies to respond to stimuli, damage, and other environmental changes. We model these adapting network architectures using a generic dynamical system on weighted graphs and find in simulation that these networks ultimately develop a hierarchical organization of the final weighted architecture accompanied by the formation of a system-spanning backbone. In addition, we find that the long term equilibration dynamics exhibit behavior reminiscent of glassy systems characterized by long periods of slow changes punctuated by bursts of reorganization events.

A Flexible System for Simulating Aeronautical Telecommunication Network

NASA Technical Reports Server (NTRS)

Maly, Kurt; Overstreet, C. M.; Andey, R.

1998-01-01

At Old Dominion University, we have built Aeronautical Telecommunication Network (ATN) Simulator with NASA being the fund provider. It provides a means to evaluate the impact of modified router scheduling algorithms on the network efficiency, to perform capacity studies on various network topologies and to monitor and study various aspects of ATN through graphical user interface (GUI). In this paper we describe briefly about the proposed ATN model and our abstraction of this model. Later we describe our simulator architecture highlighting some of the design specifications, scheduling algorithms and user interface. At the end, we have provided the results of performance studies on this simulator.

Gradient calculations for dynamic recurrent neural networks: a survey.

PubMed

Pearlmutter, B A

1995-01-01

Surveys learning algorithms for recurrent neural networks with hidden units and puts the various techniques into a common framework. The authors discuss fixed point learning algorithms, namely recurrent backpropagation and deterministic Boltzmann machines, and nonfixed point algorithms, namely backpropagation through time, Elman's history cutoff, and Jordan's output feedback architecture. Forward propagation, an on-line technique that uses adjoint equations, and variations thereof, are also discussed. In many cases, the unified presentation leads to generalizations of various sorts. The author discusses advantages and disadvantages of temporally continuous neural networks in contrast to clocked ones continues with some "tricks of the trade" for training, using, and simulating continuous time and recurrent neural networks. The author presents some simulations, and at the end, addresses issues of computational complexity and learning speed.

Prevention of Malicious Nodes Communication in MANETs by Using Authorized Tokens

NASA Astrophysics Data System (ADS)

Chandrakant, N.; Shenoy, P. Deepa; Venugopal, K. R.; Patnaik, L. M.

A rapid increase of wireless networks and mobile computing applications has changed the landscape of network security. A MANET is more susceptible to the attacks than wired network. As a result, attacks with malicious intent have been and will be devised to take advantage of these vulnerabilities and to cripple the MANET operation. Hence we need to search for new architecture and mechanisms to protect the wireless networks and mobile computing applications. In this paper, we examine the nodes that come under the vicinity of base node and members of the network and communication is provided to genuine nodes only. It is found that the proposed algorithm is a effective algorithm for security in MANETs.

Design and architecture of the Mars relay network planning and analysis framework

NASA Technical Reports Server (NTRS)

Cheung, K. M.; Lee, C. H.

2002-01-01

In this paper we describe the design and architecture of the Mars Network planning and analysis framework that supports generation and validation of efficient planning and scheduling strategy. The goals are to minimize the transmitting time, minimize the delaying time, and/or maximize the network throughputs. The proposed framework would require (1) a client-server architecture to support interactive, batch, WEB, and distributed analysis and planning applications for the relay network analysis scheme, (2) a high-fidelity modeling and simulation environment that expresses link capabilities between spacecraft to spacecraft and spacecraft to Earth stations as time-varying resources, and spacecraft activities, link priority, Solar System dynamic events, the laws of orbital mechanics, and other limiting factors as spacecraft power and thermal constraints, (3) an optimization methodology that casts the resource and constraint models into a standard linear and nonlinear constrained optimization problem that lends itself to commercial off-the-shelf (COTS)planning and scheduling algorithms.

Tiled architecture of a CNN-mostly IP system

NASA Astrophysics Data System (ADS)

Spaanenburg, Lambert; Malki, Suleyman

2009-05-01

Multi-core architectures have been popularized with the advent of the IBM CELL. On a finer grain the problems in scheduling multi-cores have already existed in the tiled architectures, such as the EPIC and Da Vinci. It is not easy to evaluate the performance of a schedule on such architecture as historical data are not available. One solution is to compile algorithms for which an optimal schedule is known by analysis. A typical example is an algorithm that is already defined in terms of many collaborating simple nodes, such as a Cellular Neural Network (CNN). A simple node with a local register stack together with a 'rotating wheel' internal communication mechanism has been proposed. Though the basic CNN allows for a tiled implementation of a tiled algorithm on a tiled structure, a practical CNN system will have to disturb this regularity by the additional need for arithmetical and logical operations. Arithmetic operations are needed for instance to accommodate for low-level image processing, while logical operations are needed to fork and merge different data streams without use of the external memory. It is found that the 'rotating wheel' internal communication mechanism still handles such mechanisms without the need for global control. Overall the CNN system provides for a practical network size as implemented on a FPGA, can be easily used as embedded IP and provides a clear benchmark for a multi-core compiler.

Low Power S-Box Architecture for AES Algorithm using Programmable Second Order Reversible Cellular Automata: An Application to WBAN.

PubMed

Gangadari, Bhoopal Rao; Ahamed, Shaik Rafi

2016-12-01

In this paper, we presented a novel approach of low energy consumption architecture of S-Box used in Advanced Encryption Standard (AES) algorithm using programmable second order reversible cellular automata (RCA 2 ). The architecture entails a low power implementation with minimal delay overhead and the performance of proposed RCA 2 based S-Box in terms of security is evaluated using the cryptographic properties such as nonlinearity, correlation immunity bias, strict avalanche criteria, entropy and also found that the proposed architecture is secure enough for cryptographic applications. Moreover, the proposed AES algorithm architecture simulation studies show that energy consumption of 68.726 nJ, power dissipation of 3.856 mW for 0.18- μm at 13.69 MHz and energy consumption of 29.408 nJ, power dissipation of 1.65 mW for 0.13- μm at 13.69 MHz. The proposed AES algorithm with RCA 2 based S-Box shows a reduction power consumption by 50 % and energy consumption by 5 % compared to best classical S-Box and composite field arithmetic based AES algorithm. Apart from that, it is also shown that RCA 2 based S-Boxes are dynamic in nature, invertible, low power dissipation compared to that of LUT based S-Box and hence suitable for Wireless Body Area Network (WBAN) applications.

Designing Artificial Neural Networks Using Particle Swarm Optimization Algorithms

PubMed Central

Vázquez, Roberto A.

2015-01-01

Artificial Neural Network (ANN) design is a complex task because its performance depends on the architecture, the selected transfer function, and the learning algorithm used to train the set of synaptic weights. In this paper we present a methodology that automatically designs an ANN using particle swarm optimization algorithms such as Basic Particle Swarm Optimization (PSO), Second Generation of Particle Swarm Optimization (SGPSO), and a New Model of PSO called NMPSO. The aim of these algorithms is to evolve, at the same time, the three principal components of an ANN: the set of synaptic weights, the connections or architecture, and the transfer functions for each neuron. Eight different fitness functions were proposed to evaluate the fitness of each solution and find the best design. These functions are based on the mean square error (MSE) and the classification error (CER) and implement a strategy to avoid overtraining and to reduce the number of connections in the ANN. In addition, the ANN designed with the proposed methodology is compared with those designed manually using the well-known Back-Propagation and Levenberg-Marquardt Learning Algorithms. Finally, the accuracy of the method is tested with different nonlinear pattern classification problems. PMID:26221132

Proceedings of the Second Joint Technology Workshop on Neural Networks and Fuzzy Logic, volume 2

NASA Technical Reports Server (NTRS)

Lea, Robert N. (Editor); Villarreal, James A. (Editor)

1991-01-01

Documented here are papers presented at the Neural Networks and Fuzzy Logic Workshop sponsored by NASA and the University of Texas, Houston. Topics addressed included adaptive systems, learning algorithms, network architectures, vision, robotics, neurobiological connections, speech recognition and synthesis, fuzzy set theory and application, control and dynamics processing, space applications, fuzzy logic and neural network computers, approximate reasoning, and multiobject decision making.

Improving Cyber-Security of Smart Grid Systems via Anomaly Detection and Linguistic Domain Knowledge

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

Ondrej Linda; Todd Vollmer; Milos Manic

The planned large scale deployment of smart grid network devices will generate a large amount of information exchanged over various types of communication networks. The implementation of these critical systems will require appropriate cyber-security measures. A network anomaly detection solution is considered in this work. In common network architectures multiple communications streams are simultaneously present, making it difficult to build an anomaly detection solution for the entire system. In addition, common anomaly detection algorithms require specification of a sensitivity threshold, which inevitably leads to a tradeoff between false positives and false negatives rates. In order to alleviate these issues, thismore » paper proposes a novel anomaly detection architecture. The designed system applies the previously developed network security cyber-sensor method to individual selected communication streams allowing for learning accurate normal network behavior models. Furthermore, the developed system dynamically adjusts the sensitivity threshold of each anomaly detection algorithm based on domain knowledge about the specific network system. It is proposed to model this domain knowledge using Interval Type-2 Fuzzy Logic rules, which linguistically describe the relationship between various features of the network communication and the possibility of a cyber attack. The proposed method was tested on experimental smart grid system demonstrating enhanced cyber-security.« less

On Maximizing the Lifetime of Wireless Sensor Networks by Optimally Assigning Energy Supplies

PubMed Central

Asorey-Cacheda, Rafael; García-Sánchez, Antonio Javier; García-Sánchez, Felipe; García-Haro, Joan; Gonzalez-Castaño, Francisco Javier

2013-01-01

The extension of the network lifetime of Wireless Sensor Networks (WSN) is an important issue that has not been appropriately solved yet. This paper addresses this concern and proposes some techniques to plan an arbitrary WSN. To this end, we suggest a hierarchical network architecture, similar to realistic scenarios, where nodes with renewable energy sources (denoted as primary nodes) carry out most message delivery tasks, and nodes equipped with conventional chemical batteries (denoted as secondary nodes) are those with less communication demands. The key design issue of this network architecture is the development of a new optimization framework to calculate the optimal assignment of renewable energy supplies (primary node assignment) to maximize network lifetime, obtaining the minimum number of energy supplies and their node assignment. We also conduct a second optimization step to additionally minimize the number of packet hops between the source and the sink. In this work, we present an algorithm that approaches the results of the optimization framework, but with much faster execution speed, which is a good alternative for large-scale WSN networks. Finally, the network model, the optimization process and the designed algorithm are further evaluated and validated by means of computer simulation under realistic conditions. The results obtained are discussed comparatively. PMID:23939582

On maximizing the lifetime of Wireless Sensor Networks by optimally assigning energy supplies.

PubMed

Asorey-Cacheda, Rafael; García-Sánchez, Antonio Javier; García-Sánchez, Felipe; García-Haro, Joan; González-Castano, Francisco Javier

2013-08-09

The extension of the network lifetime of Wireless Sensor Networks (WSN) is an important issue that has not been appropriately solved yet. This paper addresses this concern and proposes some techniques to plan an arbitrary WSN. To this end, we suggest a hierarchical network architecture, similar to realistic scenarios, where nodes with renewable energy sources (denoted as primary nodes) carry out most message delivery tasks, and nodes equipped with conventional chemical batteries (denoted as secondary nodes) are those with less communication demands. The key design issue of this network architecture is the development of a new optimization framework to calculate the optimal assignment of renewable energy supplies (primary node assignment) to maximize network lifetime, obtaining the minimum number of energy supplies and their node assignment. We also conduct a second optimization step to additionally minimize the number of packet hops between the source and the sink. In this work, we present an algorithm that approaches the results of the optimization framework, but with much faster execution speed, which is a good alternative for large-scale WSN networks. Finally, the network model, the optimization process and the designed algorithm are further evaluated and validated by means of computer simulation under realistic conditions. The results obtained are discussed comparatively.

An Novel Architecture of Large-scale Communication in IOT

NASA Astrophysics Data System (ADS)

Ma, Wubin; Deng, Su; Huang, Hongbin

2018-03-01

In recent years, many scholars have done a great deal of research on the development of Internet of Things and networked physical systems. However, few people have made the detailed visualization of the large-scale communications architecture in the IOT. In fact, the non-uniform technology between IPv6 and access points has led to a lack of broad principles of large-scale communications architectures. Therefore, this paper presents the Uni-IPv6 Access and Information Exchange Method (UAIEM), a new architecture and algorithm that addresses large-scale communications in the IOT.

Reveal, A General Reverse Engineering Algorithm for Inference of Genetic Network Architectures

NASA Technical Reports Server (NTRS)

Liang, Shoudan; Fuhrman, Stefanie; Somogyi, Roland

1998-01-01

Given the immanent gene expression mapping covering whole genomes during development, health and disease, we seek computational methods to maximize functional inference from such large data sets. Is it possible, in principle, to completely infer a complex regulatory network architecture from input/output patterns of its variables? We investigated this possibility using binary models of genetic networks. Trajectories, or state transition tables of Boolean nets, resemble time series of gene expression. By systematically analyzing the mutual information between input states and output states, one is able to infer the sets of input elements controlling each element or gene in the network. This process is unequivocal and exact for complete state transition tables. We implemented this REVerse Engineering ALgorithm (REVEAL) in a C program, and found the problem to be tractable within the conditions tested so far. For n = 50 (elements) and k = 3 (inputs per element), the analysis of incomplete state transition tables (100 state transition pairs out of a possible 10(exp 15)) reliably produced the original rule and wiring sets. While this study is limited to synchronous Boolean networks, the algorithm is generalizable to include multi-state models, essentially allowing direct application to realistic biological data sets. The ability to adequately solve the inverse problem may enable in-depth analysis of complex dynamic systems in biology and other fields.

Architectural Implications for Spatial Object Association Algorithms

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

Kumar, V S; Kurc, T; Saltz, J

2009-01-29

Spatial object association, also referred to as cross-match of spatial datasets, is the problem of identifying and comparing objects in two or more datasets based on their positions in a common spatial coordinate system. In this work, we evaluate two crossmatch algorithms that are used for astronomical sky surveys, on the following database system architecture configurations: (1) Netezza Performance Server R, a parallel database system with active disk style processing capabilities, (2) MySQL Cluster, a high-throughput network database system, and (3) a hybrid configuration consisting of a collection of independent database system instances with data replication support. Our evaluation providesmore » insights about how architectural characteristics of these systems affect the performance of the spatial crossmatch algorithms. We conducted our study using real use-case scenarios borrowed from a large-scale astronomy application known as the Large Synoptic Survey Telescope (LSST).« less

An efficient and portable SIMD algorithm for charge/current deposition in Particle-In-Cell codes

NASA Astrophysics Data System (ADS)

Vincenti, H.; Lobet, M.; Lehe, R.; Sasanka, R.; Vay, J.-L.

2017-01-01

In current computer architectures, data movement (from die to network) is by far the most energy consuming part of an algorithm (≈ 20 pJ/word on-die to ≈10,000 pJ/word on the network). To increase memory locality at the hardware level and reduce energy consumption related to data movement, future exascale computers tend to use many-core processors on each compute nodes that will have a reduced clock speed to allow for efficient cooling. To compensate for frequency decrease, machine vendors are making use of long SIMD instruction registers that are able to process multiple data with one arithmetic operator in one clock cycle. SIMD register length is expected to double every four years. As a consequence, Particle-In-Cell (PIC) codes will have to achieve good vectorization to fully take advantage of these upcoming architectures. In this paper, we present a new algorithm that allows for efficient and portable SIMD vectorization of current/charge deposition routines that are, along with the field gathering routines, among the most time consuming parts of the PIC algorithm. Our new algorithm uses a particular data structure that takes into account memory alignment constraints and avoids gather/scatter instructions that can significantly affect vectorization performances on current CPUs. The new algorithm was successfully implemented in the 3D skeleton PIC code PICSAR and tested on Haswell Xeon processors (AVX2-256 bits wide data registers). Results show a factor of × 2 to × 2.5 speed-up in double precision for particle shape factor of orders 1- 3. The new algorithm can be applied as is on future KNL (Knights Landing) architectures that will include AVX-512 instruction sets with 512 bits register lengths (8 doubles/16 singles).

Application of artificial neural network to predict clay sensitivity in a high landslide prone area using CPTu data- A case study in Southwest of Sweden

NASA Astrophysics Data System (ADS)

Shahri, Abbas; Mousavinaseri, Mahsasadat; Naderi, Shima; Espersson, Maria

2015-04-01

Application of Artificial Neural Networks (ANNs) in many areas of engineering, in particular to geotechnical engineering problems such as site characterization has demonstrated some degree of success. The present paper aims to evaluate the feasibility of several various types of ANN models to predict the clay sensitivity of soft clays form piezocone penetration test data (CPTu). To get the aim, a research database of CPTu data of 70 test points around the Göta River near the Lilli Edet in the southwest of Sweden which is a high prone land slide area were collected and considered as input for ANNs. For training algorithms the quick propagation, conjugate gradient descent, quasi-Newton, limited memory quasi-Newton and Levenberg-Marquardt were developed tested and trained using the CPTu data to provide a comparison between the results of field investigation and ANN models to estimate the clay sensitivity. The reason of using the clay sensitivity parameter in this study is due to its relation to landslides in Sweden.A special high sensitive clay namely quick clay is considered as the main responsible for experienced landslides in Sweden which has high sensitivity and prone to slide. The training and testing program was started with 3-2-1 ANN architecture structure. By testing and trying several various architecture structures and changing the hidden layer in order to have a higher output resolution the 3-4-4-3-1 architecture structure for ANN in this study was confirmed. The tested algorithm showed that increasing the hidden layers up to 4 layers in ANN can improve the results and the 3-4-4-3-1 architecture structure ANNs for prediction of clay sensitivity represent reliable and reasonable response. The obtained results showed that the conjugate gradient descent algorithm with R2=0.897 has the best performance among the tested algorithms. Keywords: clay sensitivity, landslide, Artificial Neural Network

Hybrid Neural-Network: Genetic Algorithm Technique for Aircraft Engine Performance Diagnostics Developed and Demonstrated

NASA Technical Reports Server (NTRS)

Kobayashi, Takahisa; Simon, Donald L.

2002-01-01

As part of the NASA Aviation Safety Program, a unique model-based diagnostics method that employs neural networks and genetic algorithms for aircraft engine performance diagnostics has been developed and demonstrated at the NASA Glenn Research Center against a nonlinear gas turbine engine model. Neural networks are applied to estimate the internal health condition of the engine, and genetic algorithms are used for sensor fault detection, isolation, and quantification. This hybrid architecture combines the excellent nonlinear estimation capabilities of neural networks with the capability to rank the likelihood of various faults given a specific sensor suite signature. The method requires a significantly smaller data training set than a neural network approach alone does, and it performs the combined engine health monitoring objectives of performance diagnostics and sensor fault detection and isolation in the presence of nominal and degraded engine health conditions.

Prediction of Aerodynamic Coefficients for Wind Tunnel Data using a Genetic Algorithm Optimized Neural Network

NASA Technical Reports Server (NTRS)

Rajkumar, T.; Aragon, Cecilia; Bardina, Jorge; Britten, Roy

2002-01-01

A fast, reliable way of predicting aerodynamic coefficients is produced using a neural network optimized by a genetic algorithm. Basic aerodynamic coefficients (e.g. lift, drag, pitching moment) are modelled as functions of angle of attack and Mach number. The neural network is first trained on a relatively rich set of data from wind tunnel tests of numerical simulations to learn an overall model. Most of the aerodynamic parameters can be well-fitted using polynomial functions. A new set of data, which can be relatively sparse, is then supplied to the network to produce a new model consistent with the previous model and the new data. Because the new model interpolates realistically between the sparse test data points, it is suitable for use in piloted simulations. The genetic algorithm is used to choose a neural network architecture to give best results, avoiding over-and under-fitting of the test data.

Design Principles of Regulatory Networks: Searching for the Molecular Algorithms of the Cell

PubMed Central

Lim, Wendell A.; Lee, Connie M.; Tang, Chao

2013-01-01

A challenge in biology is to understand how complex molecular networks in the cell execute sophisticated regulatory functions. Here we explore the idea that there are common and general principles that link network structures to biological functions, principles that constrain the design solutions that evolution can converge upon for accomplishing a given cellular task. We describe approaches for classifying networks based on abstract architectures and functions, rather than on the specific molecular components of the networks. For any common regulatory task, can we define the space of all possible molecular solutions? Such inverse approaches might ultimately allow the assembly of a design table of core molecular algorithms that could serve as a guide for building synthetic networks and modulating disease networks. PMID:23352241

Software-Defined Architectures for Spectrally Efficient Cognitive Networking in Extreme Environments

NASA Astrophysics Data System (ADS)

Sklivanitis, Georgios

The objective of this dissertation is the design, development, and experimental evaluation of novel algorithms and reconfigurable radio architectures for spectrally efficient cognitive networking in terrestrial, airborne, and underwater environments. Next-generation wireless communication architectures and networking protocols that maximize spectrum utilization efficiency in congested/contested or low-spectral availability (extreme) communication environments can enable a rich body of applications with unprecedented societal impact. In recent years, underwater wireless networks have attracted significant attention for military and commercial applications including oceanographic data collection, disaster prevention, tactical surveillance, offshore exploration, and pollution monitoring. Unmanned aerial systems that are autonomously networked and fully mobile can assist humans in extreme or difficult-to-reach environments and provide cost-effective wireless connectivity for devices without infrastructure coverage. Cognitive radio (CR) has emerged as a promising technology to maximize spectral efficiency in dynamically changing communication environments by adaptively reconfiguring radio communication parameters. At the same time, the fast developing technology of software-defined radio (SDR) platforms has enabled hardware realization of cognitive radio algorithms for opportunistic spectrum access. However, existing algorithmic designs and protocols for shared spectrum access do not effectively capture the interdependencies between radio parameters at the physical (PHY), medium-access control (MAC), and network (NET) layers of the network protocol stack. In addition, existing off-the-shelf radio platforms and SDR programmable architectures are far from fulfilling runtime adaptation and reconfiguration across PHY, MAC, and NET layers. Spectrum allocation in cognitive networks with multi-hop communication requirements depends on the location, network traffic load, and interference profile at each network node. As a result, the development and implementation of algorithms and cross-layer reconfigurable radio platforms that can jointly treat space, time, and frequency as a unified resource to be dynamically optimized according to inter- and intra-network interference constraints is of fundamental importance. In the next chapters, we present novel algorithmic and software/hardware implementation developments toward the deployment of spectrally efficient terrestrial, airborne, and underwater wireless networks. In Chapter 1 we review the state-of-art in commercially available SDR platforms, describe their software and hardware capabilities, and classify them based on their ability to enable rapid prototyping and advance experimental research in wireless networks. Chapter 2 discusses system design and implementation details toward real-time evaluation of a software-radio platform for all-spectrum cognitive channelization in the presence of narrowband or wideband primary stations. All-spectrum channelization is achieved by designing maximum signal-to-interference-plus-noise ratio (SINR) waveforms that span the whole continuum of the device-accessible spectrum, while satisfying peak power and interference temperature (IT) constraints for the secondary and primary users, respectively. In Chapter 3, we introduce the concept of all-spectrum channelization based on max-SINR optimized sparse-binary waveforms, we propose optimal and suboptimal waveform design algorithms, and evaluate their SINR and bit-error-rate (BER) performance in an SDR testbed. Chapter 4 considers the problem of channel estimation with minimal pilot signaling in multi-cell multi-user multi-input multi-output (MIMO) systems with very large antenna arrays at the base station, and proposes a least-squares (LS)-type algorithm that iteratively extracts channel and data estimates from a short record of data measurements. Our algorithmic developments toward spectrally-efficient cognitive networking through joint optimization of channel access code-waveforms and routes in a multi-hop network are described in Chapter 5. Algorithmic designs are software optimized on heterogeneous multi-core general-purpose processor (GPP)-based SDR architectures by leveraging a novel software-radio framework that offers self-optimization and real-time adaptation capabilities at the PHY, MAC, and NET layers of the network protocol stack. Our system design approach is experimentally validated under realistic conditions in a large-scale hybrid ground-air testbed deployment. Chapter 6 reviews the state-of-art in software and hardware platforms for underwater wireless networking and proposes a software-defined acoustic modem prototype that enables (i) cognitive reconfiguration of PHY/MAC parameters, and (ii) cross-technology communication adaptation. The proposed modem design is evaluated in terms of effective communication data rate in both water tank and lake testbed setups. In Chapter 7, we present a novel receiver configuration for code-waveform-based multiple-access underwater communications. The proposed receiver is fully reconfigurable and executes (i) all-spectrum cognitive channelization, and (ii) combined synchronization, channel estimation, and demodulation. Experimental evaluation in terms of SINR and BER show that all-spectrum channelization is a powerful proposition for underwater communications. At the same time, the proposed receiver design can significantly enhance bandwidth utilization. Finally, in Chapter 8, we focus on challenging practical issues that arise in underwater acoustic sensor network setups where co-located multi-antenna sensor deployment is not feasible due to power, computation, and hardware limitations, and design, implement, and evaluate an underwater receiver structure that accounts for multiple carrier frequency and timing offsets in virtual (distributed) MIMO underwater systems.

Boosted ARTMAP: modifications to fuzzy ARTMAP motivated by boosting theory.

PubMed

Verzi, Stephen J; Heileman, Gregory L; Georgiopoulos, Michael

2006-05-01

In this paper, several modifications to the Fuzzy ARTMAP neural network architecture are proposed for conducting classification in complex, possibly noisy, environments. The goal of these modifications is to improve upon the generalization performance of Fuzzy ART-based neural networks, such as Fuzzy ARTMAP, in these situations. One of the major difficulties of employing Fuzzy ARTMAP on such learning problems involves over-fitting of the training data. Structural risk minimization is a machine-learning framework that addresses the issue of over-fitting by providing a backbone for analysis as well as an impetus for the design of better learning algorithms. The theory of structural risk minimization reveals a trade-off between training error and classifier complexity in reducing generalization error, which will be exploited in the learning algorithms proposed in this paper. Boosted ART extends Fuzzy ART by allowing the spatial extent of each cluster formed to be adjusted independently. Boosted ARTMAP generalizes upon Fuzzy ARTMAP by allowing non-zero training error in an effort to reduce the hypothesis complexity and hence improve overall generalization performance. Although Boosted ARTMAP is strictly speaking not a boosting algorithm, the changes it encompasses were motivated by the goals that one strives to achieve when employing boosting. Boosted ARTMAP is an on-line learner, it does not require excessive parameter tuning to operate, and it reduces precisely to Fuzzy ARTMAP for particular parameter values. Another architecture described in this paper is Structural Boosted ARTMAP, which uses both Boosted ART and Boosted ARTMAP to perform structural risk minimization learning. Structural Boosted ARTMAP will allow comparison of the capabilities of off-line versus on-line learning as well as empirical risk minimization versus structural risk minimization using Fuzzy ARTMAP-based neural network architectures. Both empirical and theoretical results are presented to enhance the understanding of these architectures.

Real-time network traffic classification technique for wireless local area networks based on compressed sensing

NASA Astrophysics Data System (ADS)

Balouchestani, Mohammadreza

2017-05-01

Network traffic or data traffic in a Wireless Local Area Network (WLAN) is the amount of network packets moving across a wireless network from each wireless node to another wireless node, which provide the load of sampling in a wireless network. WLAN's Network traffic is the main component for network traffic measurement, network traffic control and simulation. Traffic classification technique is an essential tool for improving the Quality of Service (QoS) in different wireless networks in the complex applications such as local area networks, wireless local area networks, wireless personal area networks, wireless metropolitan area networks, and wide area networks. Network traffic classification is also an essential component in the products for QoS control in different wireless network systems and applications. Classifying network traffic in a WLAN allows to see what kinds of traffic we have in each part of the network, organize the various kinds of network traffic in each path into different classes in each path, and generate network traffic matrix in order to Identify and organize network traffic which is an important key for improving the QoS feature. To achieve effective network traffic classification, Real-time Network Traffic Classification (RNTC) algorithm for WLANs based on Compressed Sensing (CS) is presented in this paper. The fundamental goal of this algorithm is to solve difficult wireless network management problems. The proposed architecture allows reducing False Detection Rate (FDR) to 25% and Packet Delay (PD) to 15 %. The proposed architecture is also increased 10 % accuracy of wireless transmission, which provides a good background for establishing high quality wireless local area networks.

Multi-layer service function chaining scheduling based on auxiliary graph in IP over optical network

NASA Astrophysics Data System (ADS)

Li, Yixuan; Li, Hui; Liu, Yuze; Ji, Yuefeng

2017-10-01

Software Defined Optical Network (SDON) can be considered as extension of Software Defined Network (SDN) in optical networks. SDON offers a unified control plane and makes optical network an intelligent transport network with dynamic flexibility and service adaptability. For this reason, a comprehensive optical transmission service, able to achieve service differentiation all the way down to the optical transport layer, can be provided to service function chaining (SFC). IP over optical network, as a promising networking architecture to interconnect data centers, is the most widely used scenarios of SFC. In this paper, we offer a flexible and dynamic resource allocation method for diverse SFC service requests in the IP over optical network. To do so, we firstly propose the concept of optical service function (OSF) and a multi-layer SFC model. OSF represents the comprehensive optical transmission service (e.g., multicast, low latency, quality of service, etc.), which can be achieved in multi-layer SFC model. OSF can also be considered as a special SF. Secondly, we design a resource allocation algorithm, which we call OSF-oriented optical service scheduling algorithm. It is able to address multi-layer SFC optical service scheduling and provide comprehensive optical transmission service, while meeting multiple optical transmission requirements (e.g., bandwidth, latency, availability). Moreover, the algorithm exploits the concept of Auxiliary Graph. Finally, we compare our algorithm with the Baseline algorithm in simulation. And simulation results show that our algorithm achieves superior performance than Baseline algorithm in low traffic load condition.

Optimization of neural network architecture for classification of radar jamming FM signals

NASA Astrophysics Data System (ADS)

Soto, Alberto; Mendoza, Ariadna; Flores, Benjamin C.

2017-05-01

The purpose of this study is to investigate several artificial Neural Network (NN) architectures in order to design a cognitive radar system capable of optimally distinguishing linear Frequency-Modulated (FM) signals from bandlimited Additive White Gaussian Noise (AWGN). The goal is to create a theoretical framework to determine an optimal NN architecture to achieve a Probability of Detection (PD) of 95% or higher and a Probability of False Alarm (PFA) of 1.5% or lower at 5 dB Signal to Noise Ratio (SNR). Literature research reveals that the frequency-domain power spectral densities characterize a signal more efficiently than its time-domain counterparts. Therefore, the input data is preprocessed by calculating the magnitude square of the Discrete Fourier Transform of the digitally sampled bandlimited AWGN and linear FM signals to populate a matrix containing N number of samples and M number of spectra. This matrix is used as input for the NN, and the spectra are divided as follows: 70% for training, 15% for validation, and 15% for testing. The study begins by experimentally deducing the optimal number of hidden neurons (1-40 neurons), then the optimal number of hidden layers (1-5 layers), and lastly, the most efficient learning algorithm. The training algorithms examined are: Resilient Backpropagation, Scaled Conjugate Gradient, Conjugate Gradient with Powell/Beale Restarts, Polak-Ribiére Conjugate Gradient, and Variable Learning Rate Backpropagation. We determine that an architecture with ten hidden neurons (or higher), one hidden layer, and a Scaled Conjugate Gradient for training algorithm encapsulates an optimal architecture for our application.

Scalable Lunar Surface Networks and Adaptive Orbit Access

NASA Technical Reports Server (NTRS)

Wang, Xudong

2015-01-01

Teranovi Technologies, Inc., has developed innovative network architecture, protocols, and algorithms for both lunar surface and orbit access networks. A key component of the overall architecture is a medium access control (MAC) protocol that includes a novel mechanism of overlaying time division multiple access (TDMA) and carrier sense multiple access with collision avoidance (CSMA/CA), ensuring scalable throughput and quality of service. The new MAC protocol is compatible with legacy Institute of Electrical and Electronics Engineers (IEEE) 802.11 networks. Advanced features include efficiency power management, adaptive channel width adjustment, and error control capability. A hybrid routing protocol combines the advantages of ad hoc on-demand distance vector (AODV) routing and disruption/delay-tolerant network (DTN) routing. Performance is significantly better than AODV or DTN and will be particularly effective for wireless networks with intermittent links, such as lunar and planetary surface networks and orbit access networks.

Constructive autoassociative neural network for facial recognition.

PubMed

Fernandes, Bruno J T; Cavalcanti, George D C; Ren, Tsang I

2014-01-01

Autoassociative artificial neural networks have been used in many different computer vision applications. However, it is difficult to define the most suitable neural network architecture because this definition is based on previous knowledge and depends on the problem domain. To address this problem, we propose a constructive autoassociative neural network called CANet (Constructive Autoassociative Neural Network). CANet integrates the concepts of receptive fields and autoassociative memory in a dynamic architecture that changes the configuration of the receptive fields by adding new neurons in the hidden layer, while a pruning algorithm removes neurons from the output layer. Neurons in the CANet output layer present lateral inhibitory connections that improve the recognition rate. Experiments in face recognition and facial expression recognition show that the CANet outperforms other methods presented in the literature.

Software defined multi-OLT passive optical network for flexible traffic allocation

NASA Astrophysics Data System (ADS)

Zhang, Shizong; Gu, Rentao; Ji, Yuefeng; Zhang, Jiawei; Li, Hui

2016-10-01

With the rapid growth of 4G mobile network and vehicular network services mobile terminal users have increasing demand on data sharing among different radio remote units (RRUs) and roadside units (RSUs). Meanwhile, commercial video-streaming, video/voice conference applications delivered through peer-to-peer (P2P) technology are still keep on stimulating the sharp increment of bandwidth demand in both business and residential subscribers. However, a significant issue is that, although wavelength division multiplexing (WDM) and orthogonal frequency division multiplexing (OFDM) technology have been proposed to fulfil the ever-increasing bandwidth demand in access network, the bandwidth of optical fiber is not unlimited due to the restriction of optical component properties and modulation/demodulation technology, and blindly increase the wavelength cannot meet the cost-sensitive characteristic of the access network. In this paper, we propose a software defined multi-OLT PON architecture to support efficient scheduling of access network traffic. By introducing software defined networking technology and wavelength selective switch into TWDM PON system in central office, multiple OLTs can be considered as a bandwidth resource pool and support flexible traffic allocation for optical network units (ONUs). Moreover, under the configuration of the control plane, ONUs have the capability of changing affiliation between different OLTs under different traffic situations, thus the inter-OLT traffic can be localized and the data exchange pressure of the core network can be released. Considering this architecture is designed to be maximum following the TWDM PON specification, the existing optical distribution network (ODN) investment can be saved and conventional EPON/GPON equipment can be compatible with the proposed architecture. What's more, based on this architecture, we propose a dynamic wavelength scheduling algorithm, which can be deployed as an application on control plane and achieve effective scheduling OLT wavelength resources between different OLTs based on various traffic situation. Simulation results show that, by using the scheduling algorithm, network traffic between different OLTs can be optimized effectively, and the wavelength utilization of the multi-OLT system can be improved due to the flexible wavelength scheduling.

Robust Architectures for Complex Multi-Agent Heterogeneous Systems

DTIC Science & Technology

2014-07-23

establish the tradeoff between the control performance and the QoS of the communications network . We also derived the performance bound on the difference...accomplished within this time period leveraged the prior accomplishments in the area of networked multi-agent systems. The past work (prior to 2011...distributed control of uncertain networked systems [3]. Additionally, a preliminary collision avoidance algorithm has been developed for a team of

A hybrid linear/nonlinear training algorithm for feedforward neural networks.

PubMed

McLoone, S; Brown, M D; Irwin, G; Lightbody, A

1998-01-01

This paper presents a new hybrid optimization strategy for training feedforward neural networks. The algorithm combines gradient-based optimization of nonlinear weights with singular value decomposition (SVD) computation of linear weights in one integrated routine. It is described for the multilayer perceptron (MLP) and radial basis function (RBF) networks and then extended to the local model network (LMN), a new feedforward structure in which a global nonlinear model is constructed from a set of locally valid submodels. Simulation results are presented demonstrating the superiority of the new hybrid training scheme compared to second-order gradient methods. It is particularly effective for the LMN architecture where the linear to nonlinear parameter ratio is large.

IDMA: improving the defense against malicious attack for mobile ad hoc networks based on ARIP protocol

NASA Astrophysics Data System (ADS)

Peng, Chaorong; Chen, Chang Wen

2008-04-01

Malicious nodes are mounting increasingly sophisticated attacking operations on the Mobile Ad Hoc Networks (MANETs). This is mainly because the IP-based MANETs are vulnerable to attacks by various malicious nodes. However, the defense against malicious attack can be improved when a new layer of network architecture can be developed to separate true IP address from disclosing to the malicious nodes. In this paper, we propose a new algorithm to improve the defense against malicious attack (IDMA) that is based on a recently developed Assignment Router Identify Protocol (ARIP) for the clustering-based MANET management. In the ARIP protocol, we design the ARIP architecture based on the new Identity instead of the vulnerable IP addresses to provide the required security that is embedded seamlessly into the overall network architecture. We make full use of ARIP's special property to monitor gateway forward packets by Reply Request Route Packets (RREP) without additional intrusion detection layer. We name this new algorithm IDMA because of its inherent capability to improve the defense against malicious attacks. Through IDMA, a watching algorithm can be established so as to counterattack the malicious node in the routing path when it unusually drops up packets. We provide analysis examples for IDMA for the defense against a malicious node that disrupts the route discovery by impersonating the destination, or by responding with state of corrupted routing information, or by disseminating forged control traffic. The IDMA algorithm is able to counterattack the malicious node in the cases when the node lunch DoS attack by broadcast a large number of route requests, or make Target traffic congestion by delivering huge mount of data; or spoof the IP addresses and send forge packets with a fake ID to the same Target causing traffic congestion at that destination. We have implemented IDMA algorism using the GloMoSim simulator and have demonstrated its performance under a variety of operational conditions.

Exploring multiple feature combination strategies with a recurrent neural network architecture for off-line handwriting recognition

NASA Astrophysics Data System (ADS)

Mioulet, L.; Bideault, G.; Chatelain, C.; Paquet, T.; Brunessaux, S.

2015-01-01

The BLSTM-CTC is a novel recurrent neural network architecture that has outperformed previous state of the art algorithms in tasks such as speech recognition or handwriting recognition. It has the ability to process long term dependencies in temporal signals in order to label unsegmented data. This paper describes different ways of combining features using a BLSTM-CTC architecture. Not only do we explore the low level combination (feature space combination) but we also explore high level combination (decoding combination) and mid-level (internal system representation combination). The results are compared on the RIMES word database. Our results show that the low level combination works best, thanks to the powerful data modeling of the LSTM neurons.

Graphics Processing Unit–Enhanced Genetic Algorithms for Solving the Temporal Dynamics of Gene Regulatory Networks

PubMed Central

García-Calvo, Raúl; Guisado, JL; Diaz-del-Rio, Fernando; Córdoba, Antonio; Jiménez-Morales, Francisco

2018-01-01

Understanding the regulation of gene expression is one of the key problems in current biology. A promising method for that purpose is the determination of the temporal dynamics between known initial and ending network states, by using simple acting rules. The huge amount of rule combinations and the nonlinear inherent nature of the problem make genetic algorithms an excellent candidate for finding optimal solutions. As this is a computationally intensive problem that needs long runtimes in conventional architectures for realistic network sizes, it is fundamental to accelerate this task. In this article, we study how to develop efficient parallel implementations of this method for the fine-grained parallel architecture of graphics processing units (GPUs) using the compute unified device architecture (CUDA) platform. An exhaustive and methodical study of various parallel genetic algorithm schemes—master-slave, island, cellular, and hybrid models, and various individual selection methods (roulette, elitist)—is carried out for this problem. Several procedures that optimize the use of the GPU’s resources are presented. We conclude that the implementation that produces better results (both from the performance and the genetic algorithm fitness perspectives) is simulating a few thousands of individuals grouped in a few islands using elitist selection. This model comprises 2 mighty factors for discovering the best solutions: finding good individuals in a short number of generations, and introducing genetic diversity via a relatively frequent and numerous migration. As a result, we have even found the optimal solution for the analyzed gene regulatory network (GRN). In addition, a comparative study of the performance obtained by the different parallel implementations on GPU versus a sequential application on CPU is carried out. In our tests, a multifold speedup was obtained for our optimized parallel implementation of the method on medium class GPU over an equivalent sequential single-core implementation running on a recent Intel i7 CPU. This work can provide useful guidance to researchers in biology, medicine, or bioinformatics in how to take advantage of the parallelization on massively parallel devices and GPUs to apply novel metaheuristic algorithms powered by nature for real-world applications (like the method to solve the temporal dynamics of GRNs). PMID:29662297

Graphics Processing Unit-Enhanced Genetic Algorithms for Solving the Temporal Dynamics of Gene Regulatory Networks.

PubMed

García-Calvo, Raúl; Guisado, J L; Diaz-Del-Rio, Fernando; Córdoba, Antonio; Jiménez-Morales, Francisco

2018-01-01

Understanding the regulation of gene expression is one of the key problems in current biology. A promising method for that purpose is the determination of the temporal dynamics between known initial and ending network states, by using simple acting rules. The huge amount of rule combinations and the nonlinear inherent nature of the problem make genetic algorithms an excellent candidate for finding optimal solutions. As this is a computationally intensive problem that needs long runtimes in conventional architectures for realistic network sizes, it is fundamental to accelerate this task. In this article, we study how to develop efficient parallel implementations of this method for the fine-grained parallel architecture of graphics processing units (GPUs) using the compute unified device architecture (CUDA) platform. An exhaustive and methodical study of various parallel genetic algorithm schemes-master-slave, island, cellular, and hybrid models, and various individual selection methods (roulette, elitist)-is carried out for this problem. Several procedures that optimize the use of the GPU's resources are presented. We conclude that the implementation that produces better results (both from the performance and the genetic algorithm fitness perspectives) is simulating a few thousands of individuals grouped in a few islands using elitist selection. This model comprises 2 mighty factors for discovering the best solutions: finding good individuals in a short number of generations, and introducing genetic diversity via a relatively frequent and numerous migration. As a result, we have even found the optimal solution for the analyzed gene regulatory network (GRN). In addition, a comparative study of the performance obtained by the different parallel implementations on GPU versus a sequential application on CPU is carried out. In our tests, a multifold speedup was obtained for our optimized parallel implementation of the method on medium class GPU over an equivalent sequential single-core implementation running on a recent Intel i7 CPU. This work can provide useful guidance to researchers in biology, medicine, or bioinformatics in how to take advantage of the parallelization on massively parallel devices and GPUs to apply novel metaheuristic algorithms powered by nature for real-world applications (like the method to solve the temporal dynamics of GRNs).

Rapid Calculation of Max-Min Fair Rates for Multi-Commodity Flows in Fat-Tree Networks

DOE PAGES

Mollah, Md Atiqul; Yuan, Xin; Pakin, Scott; ...

2017-08-29

Max-min fairness is often used in the performance modeling of interconnection networks. Existing methods to compute max-min fair rates for multi-commodity flows have high complexity and are computationally infeasible for large networks. In this paper, we show that by considering topological features, this problem can be solved efficiently for the fat-tree topology that is widely used in data centers and high performance compute clusters. Several efficient new algorithms are developed for this problem, including a parallel algorithm that can take advantage of multi-core and shared-memory architectures. Using these algorithms, we demonstrate that it is possible to find the max-min fairmore » rate allocation for multi-commodity flows in fat-tree networks that support tens of thousands of nodes. We evaluate the run-time performance of the proposed algorithms and show improvement in orders of magnitude over the previously best known method. Finally, we further demonstrate a new application of max-min fair rate allocation that is only computationally feasible using our new algorithms.« less

Rapid Calculation of Max-Min Fair Rates for Multi-Commodity Flows in Fat-Tree Networks

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

Mollah, Md Atiqul; Yuan, Xin; Pakin, Scott

Max-min fairness is often used in the performance modeling of interconnection networks. Existing methods to compute max-min fair rates for multi-commodity flows have high complexity and are computationally infeasible for large networks. In this paper, we show that by considering topological features, this problem can be solved efficiently for the fat-tree topology that is widely used in data centers and high performance compute clusters. Several efficient new algorithms are developed for this problem, including a parallel algorithm that can take advantage of multi-core and shared-memory architectures. Using these algorithms, we demonstrate that it is possible to find the max-min fairmore » rate allocation for multi-commodity flows in fat-tree networks that support tens of thousands of nodes. We evaluate the run-time performance of the proposed algorithms and show improvement in orders of magnitude over the previously best known method. Finally, we further demonstrate a new application of max-min fair rate allocation that is only computationally feasible using our new algorithms.« less

Cyber Security Research Frameworks For Coevolutionary Network Defense

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

Rush, George D.; Tauritz, Daniel Remy

Several architectures have been created for developing and testing systems used in network security, but most are meant to provide a platform for running cyber security experiments as opposed to automating experiment processes. In the first paper, we propose a framework termed Distributed Cyber Security Automation Framework for Experiments (DCAFE) that enables experiment automation and control in a distributed environment. Predictive analysis of adversaries is another thorny issue in cyber security. Game theory can be used to mathematically analyze adversary models, but its scalability limitations restrict its use. Computational game theory allows us to scale classical game theory to larger,more » more complex systems. In the second paper, we propose a framework termed Coevolutionary Agent-based Network Defense Lightweight Event System (CANDLES) that can coevolve attacker and defender agent strategies and capabilities and evaluate potential solutions with a custom network defense simulation. The third paper is a continuation of the CANDLES project in which we rewrote key parts of the framework. Attackers and defenders have been redesigned to evolve pure strategy, and a new network security simulation is devised which specifies network architecture and adds a temporal aspect. We also add a hill climber algorithm to evaluate the search space and justify the use of a coevolutionary algorithm.« less

Anatomically constrained neural network models for the categorization of facial expression

NASA Astrophysics Data System (ADS)

McMenamin, Brenton W.; Assadi, Amir H.

2004-12-01

The ability to recognize facial expression in humans is performed with the amygdala which uses parallel processing streams to identify the expressions quickly and accurately. Additionally, it is possible that a feedback mechanism may play a role in this process as well. Implementing a model with similar parallel structure and feedback mechanisms could be used to improve current facial recognition algorithms for which varied expressions are a source for error. An anatomically constrained artificial neural-network model was created that uses this parallel processing architecture and feedback to categorize facial expressions. The presence of a feedback mechanism was not found to significantly improve performance for models with parallel architecture. However the use of parallel processing streams significantly improved accuracy over a similar network that did not have parallel architecture. Further investigation is necessary to determine the benefits of using parallel streams and feedback mechanisms in more advanced object recognition tasks.

Anatomically constrained neural network models for the categorization of facial expression

NASA Astrophysics Data System (ADS)

McMenamin, Brenton W.; Assadi, Amir H.

2005-01-01

The ability to recognize facial expression in humans is performed with the amygdala which uses parallel processing streams to identify the expressions quickly and accurately. Additionally, it is possible that a feedback mechanism may play a role in this process as well. Implementing a model with similar parallel structure and feedback mechanisms could be used to improve current facial recognition algorithms for which varied expressions are a source for error. An anatomically constrained artificial neural-network model was created that uses this parallel processing architecture and feedback to categorize facial expressions. The presence of a feedback mechanism was not found to significantly improve performance for models with parallel architecture. However the use of parallel processing streams significantly improved accuracy over a similar network that did not have parallel architecture. Further investigation is necessary to determine the benefits of using parallel streams and feedback mechanisms in more advanced object recognition tasks.

Investigation of rat exploratory behavior via evolving artificial neural networks.

PubMed

Costa, Ariadne de Andrade; Tinós, Renato

2016-09-01

Neuroevolution comprises the use of evolutionary computation to define the architecture and/or to train artificial neural networks (ANNs). This strategy has been employed to investigate the behavior of rats in the elevated plus-maze, which is a widely used tool for studying anxiety in mice and rats. Here we propose a neuroevolutionary model, in which both the weights and the architecture of artificial neural networks (our virtual rats) are evolved by a genetic algorithm. This model is an improvement of a previous model that involves the evolution of just the weights of the ANN by the genetic algorithm. In order to compare both models, we analyzed traditional measures of anxiety behavior, like the time spent and the number of entries in both open and closed arms of the maze. When compared to real rat data, our findings suggest that the results from the model introduced here are statistically better than those from other models in the literature. In this way, the neuroevolution of architecture is clearly important for the development of the virtual rats. Moreover, this technique allowed the comprehension of the importance of different sensory units and different number of hidden neurons (performing as memory) in the ANNs (virtual rats). Copyright © 2016 Elsevier B.V. All rights reserved.

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.

Performance and policy dimensions in internet routing

NASA Technical Reports Server (NTRS)

Mills, David L.; Boncelet, Charles G.; Elias, John G.; Schragger, Paul A.; Jackson, Alden W.; Thyagarajan, Ajit

1995-01-01

The Internet Routing Project, referred to in this report as the 'Highball Project', has been investigating architectures suitable for networks spanning large geographic areas and capable of very high data rates. The Highball network architecture is based on a high speed crossbar switch and an adaptive, distributed, TDMA scheduling algorithm. The scheduling algorithm controls the instantaneous configuration and swell time of the switch, one of which is attached to each node. In order to send a single burst or a multi-burst packet, a reservation request is sent to all nodes. The scheduling algorithm then configures the switches immediately prior to the arrival of each burst, so it can be relayed immediately without requiring local storage. Reservations and housekeeping information are sent using a special broadcast-spanning-tree schedule. Progress to date in the Highball Project includes the design and testing of a suite of scheduling algorithms, construction of software reservation/scheduling simulators, and construction of a strawman hardware and software implementation. A prototype switch controller and timestamp generator have been completed and are in test. Detailed documentation on the algorithms, protocols and experiments conducted are given in various reports and papers published. Abstracts of this literature are included in the bibliography at the end of this report, which serves as an extended executive summary.

Adaptive fuzzy system for 3-D vision

NASA Technical Reports Server (NTRS)

Mitra, Sunanda

1993-01-01

An adaptive fuzzy system using the concept of the Adaptive Resonance Theory (ART) type neural network architecture and incorporating fuzzy c-means (FCM) system equations for reclassification of cluster centers was developed. The Adaptive Fuzzy Leader Clustering (AFLC) architecture is a hybrid neural-fuzzy system which learns on-line in a stable and efficient manner. The system uses a control structure similar to that found in the Adaptive Resonance Theory (ART-1) network to identify the cluster centers initially. The initial classification of an input takes place in a two stage process; a simple competitive stage and a distance metric comparison stage. The cluster prototypes are then incrementally updated by relocating the centroid positions from Fuzzy c-Means (FCM) system equations for the centroids and the membership values. The operational characteristics of AFLC and the critical parameters involved in its operation are discussed. The performance of the AFLC algorithm is presented through application of the algorithm to the Anderson Iris data, and laser-luminescent fingerprint image data. The AFLC algorithm successfully classifies features extracted from real data, discrete or continuous, indicating the potential strength of this new clustering algorithm in analyzing complex data sets. The hybrid neuro-fuzzy AFLC algorithm will enhance analysis of a number of difficult recognition and control problems involved with Tethered Satellite Systems and on-orbit space shuttle attitude controller.

Learning and optimization with cascaded VLSI neural network building-block chips

NASA Technical Reports Server (NTRS)

Duong, T.; Eberhardt, S. P.; Tran, M.; Daud, T.; Thakoor, A. P.

1992-01-01

To demonstrate the versatility of the building-block approach, two neural network applications were implemented on cascaded analog VLSI chips. Weights were implemented using 7-b multiplying digital-to-analog converter (MDAC) synapse circuits, with 31 x 32 and 32 x 32 synapses per chip. A novel learning algorithm compatible with analog VLSI was applied to the two-input parity problem. The algorithm combines dynamically evolving architecture with limited gradient-descent backpropagation for efficient and versatile supervised learning. To implement the learning algorithm in hardware, synapse circuits were paralleled for additional quantization levels. The hardware-in-the-loop learning system allocated 2-5 hidden neurons for parity problems. Also, a 7 x 7 assignment problem was mapped onto a cascaded 64-neuron fully connected feedback network. In 100 randomly selected problems, the network found optimal or good solutions in most cases, with settling times in the range of 7-100 microseconds.

Quantitative 3D analysis of the canal network in cortical bone by micro-computed tomography.

PubMed

Cooper, D M L; Turinsky, A L; Sensen, C W; Hallgrímsson, B

2003-09-01

Cortical bone is perforated by an interconnected network of porous canals that facilitate the distribution of neurovascular structures throughout the cortex. This network is an integral component of cortical microstructure and, therefore, undergoes continual change throughout life as the cortex is remodeled. To date, the investigation of cortical microstructure, including the canal network, has largely been limited to the two-dimensional (2D) realm due to methodological hurdles. Thanks to continuing improvements in scan resolution, micro-computed tomography (muCT) is the first nondestructive imaging technology capable of resolving cortical canals. Like its application to trabecular bone, muCT provides an efficient means of quantifying aspects of 3D architecture of the canal network. Our aim here is to introduce the use of muCT for this application by providing examples, discussing some of the parameters that can be acquired, and relating these to research applications. Although several parameters developed for the analysis of trabecular microstructure are suitable for the analysis of cortical porosity, the algorithm used to estimate connectivity is not. We adapt existing algorithms based on skeletonization for this task. We believe that 3D analysis of the dimensions and architecture of the canal network will provide novel information relevant to many aspects of bone biology. For example, parameters related to the size, spacing, and volume of the canals may be particularly useful for investigation of the mechanical properties of bone. Alternatively, parameters describing the 3D architecture of the canal network, such as connectivity between the canals, may provide a means of evaluating cumulative remodeling related change. Copyright 2003 Wiley-Liss, Inc.

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.

Mark 4A antenna control system data handling architecture study

NASA Technical Reports Server (NTRS)

Briggs, H. C.; Eldred, D. B.

1991-01-01

A high-level review was conducted to provide an analysis of the existing architecture used to handle data and implement control algorithms for NASA's Deep Space Network (DSN) antennas and to make system-level recommendations for improving this architecture so that the DSN antennas can support the ever-tightening requirements of the next decade and beyond. It was found that the existing system is seriously overloaded, with processor utilization approaching 100 percent. A number of factors contribute to this overloading, including dated hardware, inefficient software, and a message-passing strategy that depends on serial connections between machines. At the same time, the system has shortcomings and idiosyncrasies that require extensive human intervention. A custom operating system kernel and an obscure programming language exacerbate the problems and should be modernized. A new architecture is presented that addresses these and other issues. Key features of the new architecture include a simplified message passing hierarchy that utilizes a high-speed local area network, redesign of particular processing function algorithms, consolidation of functions, and implementation of the architecture in modern hardware and software using mainstream computer languages and operating systems. The system would also allow incremental hardware improvements as better and faster hardware for such systems becomes available, and costs could potentially be low enough that redundancy would be provided economically. Such a system could support DSN requirements for the foreseeable future, though thorough consideration must be given to hard computational requirements, porting existing software functionality to the new system, and issues of fault tolerance and recovery.

Structure and weights optimisation of a modified Elman network emotion classifier using hybrid computational intelligence algorithms: a comparative study

NASA Astrophysics Data System (ADS)

Sheikhan, Mansour; Abbasnezhad Arabi, Mahdi; Gharavian, Davood

2015-10-01

Artificial neural networks are efficient models in pattern recognition applications, but their performance is dependent on employing suitable structure and connection weights. This study used a hybrid method for obtaining the optimal weight set and architecture of a recurrent neural emotion classifier based on gravitational search algorithm (GSA) and its binary version (BGSA), respectively. By considering the features of speech signal that were related to prosody, voice quality, and spectrum, a rich feature set was constructed. To select more efficient features, a fast feature selection method was employed. The performance of the proposed hybrid GSA-BGSA method was compared with similar hybrid methods based on particle swarm optimisation (PSO) algorithm and its binary version, PSO and discrete firefly algorithm, and hybrid of error back-propagation and genetic algorithm that were used for optimisation. Experimental tests on Berlin emotional database demonstrated the superior performance of the proposed method using a lighter network structure.

A visually guided collision warning system with a neuromorphic architecture.

PubMed

Okuno, Hirotsugu; Yagi, Tetsuya

2008-12-01

We have designed a visually guided collision warning system with a neuromorphic architecture, employing an algorithm inspired by the visual nervous system of locusts. The system was implemented with mixed analog-digital integrated circuits consisting of an analog resistive network and field-programmable gate array (FPGA) circuits. The resistive network processes the interaction between the laterally spreading excitatory and inhibitory signals instantaneously, which is essential for real-time computation of collision avoidance with a low power consumption and a compact hardware. The system responded selectively to approaching objects of simulated movie images at close range. The system was, however, confronted with serious noise problems due to the vibratory ego-motion, when it was installed in a mobile miniature car. To overcome this problem, we developed the algorithm, which is also installable in FPGA circuits, in order for the system to respond robustly during the ego-motion.

Convolutional neural networks with balanced batches for facial expressions recognition

NASA Astrophysics Data System (ADS)

Battini Sönmez, Elena; Cangelosi, Angelo

2017-03-01

This paper considers the issue of fully automatic emotion classification on 2D faces. In spite of the great effort done in recent years, traditional machine learning approaches based on hand-crafted feature extraction followed by the classification stage failed to develop a real-time automatic facial expression recognition system. The proposed architecture uses Convolutional Neural Networks (CNN), which are built as a collection of interconnected processing elements to simulate the brain of human beings. The basic idea of CNNs is to learn a hierarchical representation of the input data, which results in a better classification performance. In this work we present a block-based CNN algorithm, which uses noise, as data augmentation technique, and builds batches with a balanced number of samples per class. The proposed architecture is a very simple yet powerful CNN, which can yield state-of-the-art accuracy on the very competitive benchmark algorithm of the Extended Cohn Kanade database.

Active semi-supervised learning method with hybrid deep belief networks.

PubMed

Zhou, Shusen; Chen, Qingcai; Wang, Xiaolong

2014-01-01

In this paper, we develop a novel semi-supervised learning algorithm called active hybrid deep belief networks (AHD), to address the semi-supervised sentiment classification problem with deep learning. First, we construct the previous several hidden layers using restricted Boltzmann machines (RBM), which can reduce the dimension and abstract the information of the reviews quickly. Second, we construct the following hidden layers using convolutional restricted Boltzmann machines (CRBM), which can abstract the information of reviews effectively. Third, the constructed deep architecture is fine-tuned by gradient-descent based supervised learning with an exponential loss function. Finally, active learning method is combined based on the proposed deep architecture. We did several experiments on five sentiment classification datasets, and show that AHD is competitive with previous semi-supervised learning algorithm. Experiments are also conducted to verify the effectiveness of our proposed method with different number of labeled reviews and unlabeled reviews respectively.

Intelligent deflection routing in buffer-less networks.

PubMed

Haeri, Soroush; Trajković, Ljiljana

2015-02-01

Deflection routing is employed to ameliorate packet loss caused by contention in buffer-less architectures such as optical burst-switched networks. The main goal of deflection routing is to successfully deflect a packet based only on a limited knowledge that network nodes possess about their environment. In this paper, we present a framework that introduces intelligence to deflection routing (iDef). iDef decouples the design of the signaling infrastructure from the underlying learning algorithm. It consists of a signaling and a decision-making module. Signaling module implements a feedback management protocol while the decision-making module implements a reinforcement learning algorithm. We also propose several learning-based deflection routing protocols, implement them in iDef using the ns-3 network simulator, and compare their performance.

Call for Papers: Photonics in Switching

NASA Astrophysics Data System (ADS)

Wosinska, Lena; Glick, Madeleine

2006-04-01

Call for Papers: Photonics in Switching

Guest Editors:

Lena Wosinska, Royal Institute of Technology (KTH) / ICT Sweden Madeleine Glick, Intel Research, Cambridge, UK

Scope of Submission

• WDM node architectures
• Novel device technologies enabling photonics in switching, such as optical switch fabrics, optical memory, and wavelength conversion
• Routing protocols
• WDM switching and routing
• Quality of service
• Performance measurement and evaluation
• Next-generation optical networks: architecture, signaling, and control
• Traffic measurement and field trials
• Optical burst and packet switching
• OBS/OPS node architectures
• Burst/Packet scheduling and routing algorithms
• Contention resolution/avoidance strategies
• Services and applications for OBS/OPS (e.g., grid networks, storage-area networks, etc.)
• Burst assembly and ingress traffic shaping
• Hybrid OBS/TDM or OBS/wavelength routing

Manuscript Submission

Distributed Prognostic Health Management with Gaussian Process Regression

NASA Technical Reports Server (NTRS)

Saha, Sankalita; Saha, Bhaskar; Saxena, Abhinav; Goebel, Kai Frank

2010-01-01

Distributed prognostics architecture design is an enabling step for efficient implementation of health management systems. A major challenge encountered in such design is formulation of optimal distributed prognostics algorithms. In this paper. we present a distributed GPR based prognostics algorithm whose target platform is a wireless sensor network. In addition to challenges encountered in a distributed implementation, a wireless network poses constraints on communication patterns, thereby making the problem more challenging. The prognostics application that was used to demonstrate our new algorithms is battery prognostics. In order to present trade-offs within different prognostic approaches, we present comparison with the distributed implementation of a particle filter based prognostics for the same battery data.

Multi-agent based control of large-scale complex systems employing distributed dynamic inference engine

NASA Astrophysics Data System (ADS)

Zhang, Daili

Increasing societal demand for automation has led to considerable efforts to control large-scale complex systems, especially in the area of autonomous intelligent control methods. The control system of a large-scale complex system needs to satisfy four system level requirements: robustness, flexibility, reusability, and scalability. Corresponding to the four system level requirements, there arise four major challenges. First, it is difficult to get accurate and complete information. Second, the system may be physically highly distributed. Third, the system evolves very quickly. Fourth, emergent global behaviors of the system can be caused by small disturbances at the component level. The Multi-Agent Based Control (MABC) method as an implementation of distributed intelligent control has been the focus of research since the 1970s, in an effort to solve the above-mentioned problems in controlling large-scale complex systems. However, to the author's best knowledge, all MABC systems for large-scale complex systems with significant uncertainties are problem-specific and thus difficult to extend to other domains or larger systems. This situation is partly due to the control architecture of multiple agents being determined by agent to agent coupling and interaction mechanisms. Therefore, the research objective of this dissertation is to develop a comprehensive, generalized framework for the control system design of general large-scale complex systems with significant uncertainties, with the focus on distributed control architecture design and distributed inference engine design. A Hybrid Multi-Agent Based Control (HyMABC) architecture is proposed by combining hierarchical control architecture and module control architecture with logical replication rings. First, it decomposes a complex system hierarchically; second, it combines the components in the same level as a module, and then designs common interfaces for all of the components in the same module; third, replications are made for critical agents and are organized into logical rings. This architecture maintains clear guidelines for complexity decomposition and also increases the robustness of the whole system. Multiple Sectioned Dynamic Bayesian Networks (MSDBNs) as a distributed dynamic probabilistic inference engine, can be embedded into the control architecture to handle uncertainties of general large-scale complex systems. MSDBNs decomposes a large knowledge-based system into many agents. Each agent holds its partial perspective of a large problem domain by representing its knowledge as a Dynamic Bayesian Network (DBN). Each agent accesses local evidence from its corresponding local sensors and communicates with other agents through finite message passing. If the distributed agents can be organized into a tree structure, satisfying the running intersection property and d-sep set requirements, globally consistent inferences are achievable in a distributed way. By using different frequencies for local DBN agent belief updating and global system belief updating, it balances the communication cost with the global consistency of inferences. In this dissertation, a fully factorized Boyen-Koller (BK) approximation algorithm is used for local DBN agent belief updating, and the static Junction Forest Linkage Tree (JFLT) algorithm is used for global system belief updating. MSDBNs assume a static structure and a stable communication network for the whole system. However, for a real system, sub-Bayesian networks as nodes could be lost, and the communication network could be shut down due to partial damage in the system. Therefore, on-line and automatic MSDBNs structure formation is necessary for making robust state estimations and increasing survivability of the whole system. A Distributed Spanning Tree Optimization (DSTO) algorithm, a Distributed D-Sep Set Satisfaction (DDSSS) algorithm, and a Distributed Running Intersection Satisfaction (DRIS) algorithm are proposed in this dissertation. Combining these three distributed algorithms and a Distributed Belief Propagation (DBP) algorithm in MSDBNs makes state estimations robust to partial damage in the whole system. Combining the distributed control architecture design and the distributed inference engine design leads to a process of control system design for a general large-scale complex system. As applications of the proposed methodology, the control system design of a simplified ship chilled water system and a notional ship chilled water system have been demonstrated step by step. Simulation results not only show that the proposed methodology gives a clear guideline for control system design for general large-scale complex systems with dynamic and uncertain environment, but also indicate that the combination of MSDBNs and HyMABC can provide excellent performance for controlling general large-scale complex systems.

A rapid learning and dynamic stepwise updating algorithm for flat neural networks and the application to time-series prediction.

PubMed

Chen, C P; Wan, J Z

1999-01-01

A fast learning algorithm is proposed to find an optimal weights of the flat neural networks (especially, the functional-link network). Although the flat networks are used for nonlinear function approximation, they can be formulated as linear systems. Thus, the weights of the networks can be solved easily using a linear least-square method. This formulation makes it easier to update the weights instantly for both a new added pattern and a new added enhancement node. A dynamic stepwise updating algorithm is proposed to update the weights of the system on-the-fly. The model is tested on several time-series data including an infrared laser data set, a chaotic time-series, a monthly flour price data set, and a nonlinear system identification problem. The simulation results are compared to existing models in which more complex architectures and more costly training are needed. The results indicate that the proposed model is very attractive to real-time processes.

The 2nd Symposium on the Frontiers of Massively Parallel Computations

NASA Technical Reports Server (NTRS)

Mills, Ronnie (Editor)

1988-01-01

Programming languages, computer graphics, neural networks, massively parallel computers, SIMD architecture, algorithms, digital terrain models, sort computation, simulation of charged particle transport on the massively parallel processor and image processing are among the topics discussed.

Proceedings of the Second Joint Technology Workshop on Neural Networks and Fuzzy Logic, volume 1

NASA Technical Reports Server (NTRS)

Lea, Robert N. (Editor); Villarreal, James (Editor)

1991-01-01

Documented here are papers presented at the Neural Networks and Fuzzy Logic Workshop sponsored by NASA and the University of Houston, Clear Lake. The workshop was held April 11 to 13 at the Johnson Space Flight Center. Technical topics addressed included adaptive systems, learning algorithms, network architectures, vision, robotics, neurobiological connections, speech recognition and synthesis, fuzzy set theory and application, control and dynamics processing, space applications, fuzzy logic and neural network computers, approximate reasoning, and multiobject decision making.

Inter-Vehicular Ad Hoc Networks: From the Ground Truth to Algorithm Design and Testbed Architecture

ERIC Educational Resources Information Center

Giordano, Eugenio

2011-01-01

Many of the devices we interact with on a daily basis are currently equipped with wireless connectivity. Soon this will be extended to the vehicles we drive/ride every day. Wirelessly connected vehicles will form a new kind of network that will enable a wide set of innovative applications ranging from enhanced safety to entertainment. To…

Photoacoustic image reconstruction via deep learning

NASA Astrophysics Data System (ADS)

Antholzer, Stephan; Haltmeier, Markus; Nuster, Robert; Schwab, Johannes

2018-02-01

Applying standard algorithms to sparse data problems in photoacoustic tomography (PAT) yields low-quality images containing severe under-sampling artifacts. To some extent, these artifacts can be reduced by iterative image reconstruction algorithms which allow to include prior knowledge such as smoothness, total variation (TV) or sparsity constraints. These algorithms tend to be time consuming as the forward and adjoint problems have to be solved repeatedly. Further, iterative algorithms have additional drawbacks. For example, the reconstruction quality strongly depends on a-priori model assumptions about the objects to be recovered, which are often not strictly satisfied in practical applications. To overcome these issues, in this paper, we develop direct and efficient reconstruction algorithms based on deep learning. As opposed to iterative algorithms, we apply a convolutional neural network, whose parameters are trained before the reconstruction process based on a set of training data. For actual image reconstruction, a single evaluation of the trained network yields the desired result. Our presented numerical results (using two different network architectures) demonstrate that the proposed deep learning approach reconstructs images with a quality comparable to state of the art iterative reconstruction methods.

Toolkits and Libraries for Deep Learning.

PubMed

Erickson, Bradley J; Korfiatis, Panagiotis; Akkus, Zeynettin; Kline, Timothy; Philbrick, Kenneth

2017-08-01

Deep learning is an important new area of machine learning which encompasses a wide range of neural network architectures designed to complete various tasks. In the medical imaging domain, example tasks include organ segmentation, lesion detection, and tumor classification. The most popular network architecture for deep learning for images is the convolutional neural network (CNN). Whereas traditional machine learning requires determination and calculation of features from which the algorithm learns, deep learning approaches learn the important features as well as the proper weighting of those features to make predictions for new data. In this paper, we will describe some of the libraries and tools that are available to aid in the construction and efficient execution of deep learning as applied to medical images.

(abstract) A High Throughput 3-D Inner Product Processor

NASA Technical Reports Server (NTRS)

Daud, Tuan

1996-01-01

A particularily challenging image processing application is the real time scene acquisition and object discrimination. It requires spatio-temporal recognition of point and resolved objects at high speeds with parallel processing algorithms. Neural network paradigms provide fine grain parallism and, when implemented in hardware, offer orders of magnitude speed up. However, neural networks implemented on a VLSI chip are planer architectures capable of efficient processing of linear vector signals rather than 2-D images. Therefore, for processing of images, a 3-D stack of neural-net ICs receiving planar inputs and consuming minimal power are required. Details of the circuits with chip architectures will be described with need to develop ultralow-power electronics. Further, use of the architecture in a system for high-speed processing will be illustrated.

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.

Solving graph data issues using a layered architecture approach with applications to web spam detection.

PubMed

Scarselli, Franco; Tsoi, Ah Chung; Hagenbuchner, Markus; Noi, Lucia Di

2013-12-01

This paper proposes the combination of two state-of-the-art algorithms for processing graph input data, viz., the probabilistic mapping graph self organizing map, an unsupervised learning approach, and the graph neural network, a supervised learning approach. We organize these two algorithms in a cascade architecture containing a probabilistic mapping graph self organizing map, and a graph neural network. We show that this combined approach helps us to limit the long-term dependency problem that exists when training the graph neural network resulting in an overall improvement in performance. This is demonstrated in an application to a benchmark problem requiring the detection of spam in a relatively large set of web sites. It is found that the proposed method produces results which reach the state of the art when compared with some of the best results obtained by others using quite different approaches. A particular strength of our method is its applicability towards any input domain which can be represented as a graph. Copyright © 2013 Elsevier Ltd. All rights reserved.

Using architecture information and real-time resource state to reduce power consumption and communication costs in parallel applications.

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

Brandt, James M.; Devine, Karen Dragon; Gentile, Ann C.

2014-09-01

As computer systems grow in both size and complexity, the need for applications and run-time systems to adjust to their dynamic environment also grows. The goal of the RAAMP LDRD was to combine static architecture information and real-time system state with algorithms to conserve power, reduce communication costs, and avoid network contention. We devel- oped new data collection and aggregation tools to extract static hardware information (e.g., node/core hierarchy, network routing) as well as real-time performance data (e.g., CPU uti- lization, power consumption, memory bandwidth saturation, percentage of used bandwidth, number of network stalls). We created application interfaces that allowedmore » this data to be used easily by algorithms. Finally, we demonstrated the benefit of integrating system and application information for two use cases. The first used real-time power consumption and memory bandwidth saturation data to throttle concurrency to save power without increasing application execution time. The second used static or real-time network traffic information to reduce or avoid network congestion by remapping MPI tasks to allocated processors. Results from our work are summarized in this report; more details are available in our publications [2, 6, 14, 16, 22, 29, 38, 44, 51, 54].« less

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

DTIC Science & Technology

1993-12-31

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

Functional expansion representations of artificial neural networks

NASA Technical Reports Server (NTRS)

Gray, W. Steven

1992-01-01

In the past few years, significant interest has developed in using artificial neural networks to model and control nonlinear dynamical systems. While there exists many proposed schemes for accomplishing this and a wealth of supporting empirical results, most approaches to date tend to be ad hoc in nature and rely mainly on heuristic justifications. The purpose of this project was to further develop some analytical tools for representing nonlinear discrete-time input-output systems, which when applied to neural networks would give insight on architecture selection, pruning strategies, and learning algorithms. A long term goal is to determine in what sense, if any, a neural network can be used as a universal approximator for nonliner input-output maps with memory (i.e., realized by a dynamical system). This property is well known for the case of static or memoryless input-output maps. The general architecture under consideration in this project was a single-input, single-output recurrent feedforward network.

Artificial neural network based modelling approach for municipal solid waste gasification in a fluidized bed reactor.

PubMed

Pandey, Daya Shankar; Das, Saptarshi; Pan, Indranil; Leahy, James J; Kwapinski, Witold

2016-12-01

In this paper, multi-layer feed forward neural networks are used to predict the lower heating value of gas (LHV), lower heating value of gasification products including tars and entrained char (LHV p ) and syngas yield during gasification of municipal solid waste (MSW) during gasification in a fluidized bed reactor. These artificial neural networks (ANNs) with different architectures are trained using the Levenberg-Marquardt (LM) back-propagation algorithm and a cross validation is also performed to ensure that the results generalise to other unseen datasets. A rigorous study is carried out on optimally choosing the number of hidden layers, number of neurons in the hidden layer and activation function in a network using multiple Monte Carlo runs. Nine input and three output parameters are used to train and test various neural network architectures in both multiple output and single output prediction paradigms using the available experimental datasets. The model selection procedure is carried out to ascertain the best network architecture in terms of predictive accuracy. The simulation results show that the ANN based methodology is a viable alternative which can be used to predict the performance of a fluidized bed gasifier. Copyright © 2016 Elsevier Ltd. All rights reserved.

Simulation of the mechanical behavior of random fiber networks with different microstructure.

PubMed

Hatami-Marbini, H

2018-05-24

Filamentous protein networks are broadly encountered in biological systems such as cytoskeleton and extracellular matrix. Many numerical studies have been conducted to better understand the fundamental mechanisms behind the striking mechanical properties of these networks. In most of these previous numerical models, the Mikado algorithm has been used to represent the network microstructure. Here, a different algorithm is used to create random fiber networks in order to investigate possible roles of architecture on the elastic behavior of filamentous networks. In particular, random fibrous structures are generated from the growth of individual fibers from random nucleation points. We use computer simulations to determine the mechanical behavior of these networks in terms of their model parameters. The findings are presented and discussed along with the response of Mikado fiber networks. We demonstrate that these alternative networks and Mikado networks show a qualitatively similar response. Nevertheless, the overall elasticity of Mikado networks is stiffer compared to that of the networks created using the alternative algorithm. We describe the effective elasticity of both network types as a function of their line density and of the material properties of the filaments. We also characterize the ratio of bending and axial energy and discuss the behavior of these networks in terms of their fiber density distribution and coordination number.

Application of ant colony Algorithm and particle swarm optimization in architectural design

NASA Astrophysics Data System (ADS)

Song, Ziyi; Wu, Yunfa; Song, Jianhua

2018-02-01

By studying the development of ant colony algorithm and particle swarm algorithm, this paper expounds the core idea of the algorithm, explores the combination of algorithm and architectural design, sums up the application rules of intelligent algorithm in architectural design, and combines the characteristics of the two algorithms, obtains the research route and realization way of intelligent algorithm in architecture design. To establish algorithm rules to assist architectural design. Taking intelligent algorithm as the beginning of architectural design research, the authors provide the theory foundation of ant colony Algorithm and particle swarm algorithm in architectural design, popularize the application range of intelligent algorithm in architectural design, and provide a new idea for the architects.

On implementation of DCTCP on three-tier and fat-tree data center network topologies.

PubMed

Zafar, Saima; Bashir, Abeer; Chaudhry, Shafique Ahmad

2016-01-01

A data center is a facility for housing computational and storage systems interconnected through a communication network called data center network (DCN). Due to a tremendous growth in the computational power, storage capacity and the number of inter-connected servers, the DCN faces challenges concerning efficiency, reliability and scalability. Although transmission control protocol (TCP) is a time-tested transport protocol in the Internet, DCN challenges such as inadequate buffer space in switches and bandwidth limitations have prompted the researchers to propose techniques to improve TCP performance or design new transport protocols for DCN. Data center TCP (DCTCP) emerge as one of the most promising solutions in this domain which employs the explicit congestion notification feature of TCP to enhance the TCP congestion control algorithm. While DCTCP has been analyzed for two-tier tree-based DCN topology for traffic between servers in the same rack which is common in cloud applications, it remains oblivious to the traffic patterns common in university and private enterprise networks which traverse the complete network interconnect spanning upper tier layers. We also recognize that DCTCP performance cannot remain unaffected by the underlying DCN architecture hence there is a need to test and compare DCTCP performance when implemented over diverse DCN architectures. Some of the most notable DCN architectures are the legacy three-tier, fat-tree, BCube, DCell, VL2, and CamCube. In this research, we simulate the two switch-centric DCN architectures; the widely deployed legacy three-tier architecture and the promising fat-tree architecture using network simulator and analyze the performance of DCTCP in terms of throughput and delay for realistic traffic patterns. We also examine how DCTCP prevents incast and outcast congestion when realistic DCN traffic patterns are employed in above mentioned topologies. Our results show that the underlying DCN architecture significantly impacts DCTCP performance. We find that DCTCP gives optimal performance in fat-tree topology and is most suitable for large networks.

Event detection in an assisted living environment.

PubMed

Stroiescu, Florin; Daly, Kieran; Kuris, Benjamin

2011-01-01

This paper presents the design of a wireless event detection and in building location awareness system. The systems architecture is based on using a body worn sensor to detect events such as falls where they occur in an assisted living environment. This process involves developing event detection algorithms and transmitting such events wirelessly to an in house network based on the 802.15.4 protocol. The network would then generate alerts both in the assisted living facility and remotely to an offsite monitoring facility. The focus of this paper is on the design of the system architecture and the compliance challenges in applying this technology.

Compact OXC architecture, design and prototype development for flexible waveband routing optical networks.

PubMed

Ishikawa, Tomohiro; Mori, Yojiro; Hasegawa, Hiroshi; Subramaniam, Suresh; Sato, Ken-Ichi; Moriwaki, Osamu

2017-07-10

A novel compact OXC node architecture that combines WSSs and arrays of small scale optical delivery-coupling type switches ("DCSWs") is proposed. Unlike conventional OXC nodes, the WSSs are only responsible for dynamic path bundling ("flexible waveband") while the small scale optical switches route bundled path groups. A network design algorithm that is aware of the routing scheme is also proposed, and numerical experiments elucidate that the necessary number of WSSs and amplifiers can be significantly reduced. A prototype of the proposed OXC is also developed using monolithic arrayed DCSWs. Transmission experiments on the prototype verify the proposal's technical feasibility.

[A telemedicine electrocardiography system based on the component-architecture soft].

PubMed

Potapov, I V; Selishchev, S V

2004-01-01

The paper deals with a universal component-oriented architecture for creating the telemedicine applications. The worked-out system ensures the ECG reading, pressure measurements and pulsometry. The system design comprises a central database server and a client telemedicine module. Data can be transmitted via different interfaces--from an ordinary local network to digital satellite phones. The data protection is guaranteed by microchip charts that were used to realize the authentication 3DES algorithm.

A P2P Botnet detection scheme based on decision tree and adaptive multilayer neural networks.

PubMed

Alauthaman, Mohammad; Aslam, Nauman; Zhang, Li; Alasem, Rafe; Hossain, M A

2018-01-01

In recent years, Botnets have been adopted as a popular method to carry and spread many malicious codes on the Internet. These malicious codes pave the way to execute many fraudulent activities including spam mail, distributed denial-of-service attacks and click fraud. While many Botnets are set up using centralized communication architecture, the peer-to-peer (P2P) Botnets can adopt a decentralized architecture using an overlay network for exchanging command and control data making their detection even more difficult. This work presents a method of P2P Bot detection based on an adaptive multilayer feed-forward neural network in cooperation with decision trees. A classification and regression tree is applied as a feature selection technique to select relevant features. With these features, a multilayer feed-forward neural network training model is created using a resilient back-propagation learning algorithm. A comparison of feature set selection based on the decision tree, principal component analysis and the ReliefF algorithm indicated that the neural network model with features selection based on decision tree has a better identification accuracy along with lower rates of false positives. The usefulness of the proposed approach is demonstrated by conducting experiments on real network traffic datasets. In these experiments, an average detection rate of 99.08 % with false positive rate of 0.75 % was observed.

Architecture and design of optical path networks utilizing waveband virtual links

NASA Astrophysics Data System (ADS)

Ito, Yusaku; Mori, Yojiro; Hasegawa, Hiroshi; Sato, Ken-ichi

2016-02-01

We propose a novel optical network architecture that uses waveband virtual links, each of which can carry several optical paths, to directly bridge distant node pairs. Future photonic networks should not only transparently cover extended areas but also expand fiber capacity. However, the traversal of many ROADM nodes impairs the optical signal due to spectrum narrowing. To suppress the degradation, the bandwidth of guard bands needs to be increased, which degrades fiber frequency utilization. Waveband granular switching allows us to apply broader pass-band filtering at ROADMs and to insert sufficient guard bands between wavebands with minimum frequency utilization offset. The scheme resolves the severe spectrum narrowing effect. Moreover, the guard band between optical channels in a waveband can be minimized, which increases the number of paths that can be accommodated per fiber. In the network, wavelength path granular routing is done without utilizing waveband virtual links, and it still suffers from spectrum narrowing. A novel network design algorithm that can bound the spectrum narrowing effect by limiting the number of hops (traversed nodes that need wavelength path level routing) is proposed in this paper. This algorithm dynamically changes the waveband virtual link configuration according to the traffic distribution variation, where optical paths that need many node hops are effectively carried by virtual links. Numerical experiments demonstrate that the number of necessary fibers is reduced by 23% compared with conventional optical path networks.

An intelligent allocation algorithm for parallel processing

NASA Technical Reports Server (NTRS)

Carroll, Chester C.; Homaifar, Abdollah; Ananthram, Kishan G.

1988-01-01

The problem of allocating nodes of a program graph to processors in a parallel processing architecture is considered. The algorithm is based on critical path analysis, some allocation heuristics, and the execution granularity of nodes in a program graph. These factors, and the structure of interprocessor communication network, influence the allocation. To achieve realistic estimations of the executive durations of allocations, the algorithm considers the fact that nodes in a program graph have to communicate through varying numbers of tokens. Coarse and fine granularities have been implemented, with interprocessor token-communication duration, varying from zero up to values comparable to the execution durations of individual nodes. The effect on allocation of communication network structures is demonstrated by performing allocations for crossbar (non-blocking) and star (blocking) networks. The algorithm assumes the availability of as many processors as it needs for the optimal allocation of any program graph. Hence, the focus of allocation has been on varying token-communication durations rather than varying the number of processors. The algorithm always utilizes as many processors as necessary for the optimal allocation of any program graph, depending upon granularity and characteristics of the interprocessor communication network.

Data fusion for target tracking and classification with wireless sensor network

NASA Astrophysics Data System (ADS)

Pannetier, Benjamin; Doumerc, Robin; Moras, Julien; Dezert, Jean; Canevet, Loic

2016-10-01

In this paper, we address the problem of multiple ground target tracking and classification with information obtained from a unattended wireless sensor network. A multiple target tracking (MTT) algorithm, taking into account road and vegetation information, is proposed based on a centralized architecture. One of the key issue is how to adapt classical MTT approach to satisfy embedded processing. Based on track statistics, the classification algorithm uses estimated location, velocity and acceleration to help to classify targets. The algorithms enables tracking human and vehicles driving both on and off road. We integrate road or trail width and vegetation cover, as constraints in target motion models to improve performance of tracking under constraint with classification fusion. Our algorithm also presents different dynamic models, to palliate the maneuvers of targets. The tracking and classification algorithms are integrated into an operational platform (the fusion node). In order to handle realistic ground target tracking scenarios, we use an autonomous smart computer deposited in the surveillance area. After the calibration step of the heterogeneous sensor network, our system is able to handle real data from a wireless ground sensor network. The performance of system is evaluated in a real exercise for intelligence operation ("hunter hunt" scenario).

The influence of omniscient technology on cryptography

NASA Astrophysics Data System (ADS)

Huang, Weihong; Li, Jian

2009-07-01

Scholars agree that concurrent algorithms are an interesting new topic in the field of cyberinformatics, and hackers worldwide concur. In fact, few end-users would disagree with the evaluation of architecture. We propose a Bayesian tool for harnessing massive multiplayer online role-playing games (FIRER), which we use to prove that the well-known ubiquitous algorithm for the improvement of wide-area networks by Karthik Lakshminarayanan is in Co-NP.

Novel probabilistic neuroclassifier

NASA Astrophysics Data System (ADS)

Hong, Jiang; Serpen, Gursel

2003-09-01

A novel probabilistic potential function neural network classifier algorithm to deal with classes which are multi-modally distributed and formed from sets of disjoint pattern clusters is proposed in this paper. The proposed classifier has a number of desirable properties which distinguish it from other neural network classifiers. A complete description of the algorithm in terms of its architecture and the pseudocode is presented. Simulation analysis of the newly proposed neuro-classifier algorithm on a set of benchmark problems is presented. Benchmark problems tested include IRIS, Sonar, Vowel Recognition, Two-Spiral, Wisconsin Breast Cancer, Cleveland Heart Disease and Thyroid Gland Disease. Simulation results indicate that the proposed neuro-classifier performs consistently better for a subset of problems for which other neural classifiers perform relatively poorly.

Efficient Online Learning Algorithms Based on LSTM Neural Networks.

PubMed

Ergen, Tolga; Kozat, Suleyman Serdar

2017-09-13

We investigate online nonlinear regression and introduce novel regression structures based on the long short term memory (LSTM) networks. For the introduced structures, we also provide highly efficient and effective online training methods. To train these novel LSTM-based structures, we put the underlying architecture in a state space form and introduce highly efficient and effective particle filtering (PF)-based updates. We also provide stochastic gradient descent and extended Kalman filter-based updates. Our PF-based training method guarantees convergence to the optimal parameter estimation in the mean square error sense provided that we have a sufficient number of particles and satisfy certain technical conditions. More importantly, we achieve this performance with a computational complexity in the order of the first-order gradient-based methods by controlling the number of particles. Since our approach is generic, we also introduce a gated recurrent unit (GRU)-based approach by directly replacing the LSTM architecture with the GRU architecture, where we demonstrate the superiority of our LSTM-based approach in the sequential prediction task via different real life data sets. In addition, the experimental results illustrate significant performance improvements achieved by the introduced algorithms with respect to the conventional methods over several different benchmark real life data sets.

Prediction of Aerodynamic Coefficient using Genetic Algorithm Optimized Neural Network for Sparse Data

NASA Technical Reports Server (NTRS)

Rajkumar, T.; Bardina, Jorge; Clancy, Daniel (Technical Monitor)

2002-01-01

Wind tunnels use scale models to characterize aerodynamic coefficients, Wind tunnel testing can be slow and costly due to high personnel overhead and intensive power utilization. Although manual curve fitting can be done, it is highly efficient to use a neural network to define the complex relationship between variables. Numerical simulation of complex vehicles on the wide range of conditions required for flight simulation requires static and dynamic data. Static data at low Mach numbers and angles of attack may be obtained with simpler Euler codes. Static data of stalled vehicles where zones of flow separation are usually present at higher angles of attack require Navier-Stokes simulations which are costly due to the large processing time required to attain convergence. Preliminary dynamic data may be obtained with simpler methods based on correlations and vortex methods; however, accurate prediction of the dynamic coefficients requires complex and costly numerical simulations. A reliable and fast method of predicting complex aerodynamic coefficients for flight simulation I'S presented using a neural network. The training data for the neural network are derived from numerical simulations and wind-tunnel experiments. The aerodynamic coefficients are modeled as functions of the flow characteristics and the control surfaces of the vehicle. The basic coefficients of lift, drag and pitching moment are expressed as functions of angles of attack and Mach number. The modeled and training aerodynamic coefficients show good agreement. This method shows excellent potential for rapid development of aerodynamic models for flight simulation. Genetic Algorithms (GA) are used to optimize a previously built Artificial Neural Network (ANN) that reliably predicts aerodynamic coefficients. Results indicate that the GA provided an efficient method of optimizing the ANN model to predict aerodynamic coefficients. The reliability of the ANN using the GA includes prediction of aerodynamic coefficients to an accuracy of 110% . In our problem, we would like to get an optimized neural network architecture and minimum data set. This has been accomplished within 500 training cycles of a neural network. After removing training pairs (outliers), the GA has produced much better results. The neural network constructed is a feed forward neural network with a back propagation learning mechanism. The main goal has been to free the network design process from constraints of human biases, and to discover better forms of neural network architectures. The automation of the network architecture search by genetic algorithms seems to have been the best way to achieve this goal.

Modeling evolution of crosstalk in noisy signal transduction networks

NASA Astrophysics Data System (ADS)

Tareen, Ammar; Wingreen, Ned S.; Mukhopadhyay, Ranjan

2018-02-01

Signal transduction networks can form highly interconnected systems within cells due to crosstalk between constituent pathways. To better understand the evolutionary design principles underlying such networks, we study the evolution of crosstalk for two parallel signaling pathways that arise via gene duplication. We use a sequence-based evolutionary algorithm and evolve the network based on two physically motivated fitness functions related to information transmission. We find that one fitness function leads to a high degree of crosstalk while the other leads to pathway specificity. Our results offer insights on the relationship between network architecture and information transmission for noisy biomolecular networks.

Adaptive fuzzy leader clustering of complex data sets in pattern recognition

NASA Technical Reports Server (NTRS)

Newton, Scott C.; Pemmaraju, Surya; Mitra, Sunanda

1992-01-01

A modular, unsupervised neural network architecture for clustering and classification of complex data sets is presented. The adaptive fuzzy leader clustering (AFLC) architecture is a hybrid neural-fuzzy system that learns on-line in a stable and efficient manner. The initial classification is performed in two stages: a simple competitive stage and a distance metric comparison stage. The cluster prototypes are then incrementally updated by relocating the centroid positions from fuzzy C-means system equations for the centroids and the membership values. The AFLC algorithm is applied to the Anderson Iris data and laser-luminescent fingerprint image data. It is concluded that the AFLC algorithm successfully classifies features extracted from real data, discrete or continuous.

Development of automated system based on neural network algorithm for detecting defects on molds installed on casting machines

NASA Astrophysics Data System (ADS)

Bazhin, V. Yu; Danilov, I. V.; Petrov, P. A.

2018-05-01

During the casting of light alloys and ligatures based on aluminum and magnesium, problems of the qualitative distribution of the metal and its crystallization in the mold arise. To monitor the defects of molds on the casting conveyor, a camera with a resolution of 780 x 580 pixels and a shooting rate of 75 frames per second was selected. Images of molds from casting machines were used as input data for neural network algorithm. On the preparation of a digital database and its analytical evaluation stage, the architecture of the convolutional neural network was chosen for the algorithm. The information flow from the local controller is transferred to the OPC server and then to the SCADA system of foundry. After the training, accuracy of neural network defect recognition was about 95.1% on a validation split. After the training, weight coefficients of the neural network were used on testing split and algorithm had identical accuracy with validation images. The proposed technical solutions make it possible to increase the efficiency of the automated process control system in the foundry by expanding the digital database.

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.

A novel digital pulse processing architecture for nuclear instrumentation

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

Moline, Yoann; Thevenin, Mathieu; Corre, Gwenole

The field of nuclear instrumentation covers a wide range of applications, including counting, spectrometry, pulse shape discrimination and multi-channel coincidence. These applications are the topic of many researches, new algorithms and implementations are constantly proposed thanks to advances in digital signal processing. However, these improvements are not yet implemented in instrumentation devices. This is especially true for neutron-gamma discrimination applications which traditionally use charge comparison method while literature proposes other algorithms based on frequency domain or wavelet theory which show better performances. Another example is pileups which are generally rejected while pileup correction algorithms also exist. These processes are traditionallymore » performed offline due to two issues. The first is the Poissonian characteristic of the signal, composed of random arrival pulses which requires to current architectures to work in data flow. The second is the real-time requirement, which implies losing pulses when the pulse rate is too high. Despite the possibility of treating the pulses independently from each other, current architectures paralyze the acquisition of the signal during the processing of a pulse. This loss is called dead-time. These two issues have led current architectures to use dedicated solutions based on re-configurable components like Field Programmable Gate Arrays (FPGAs) to overcome the need of performance necessary to deal with dead-time. However, dedicated hardware algorithm implementations on re-configurable technologies are complex and time-consuming. For all these reasons, a programmable Digital pulse Processing (DPP) architecture in a high level language such as Cor C++ which can reduce dead-time would be worthwhile for nuclear instrumentation. This would reduce prototyping and test duration by reducing the level of hardware expertise to implement new algorithms. However, today's programmable solutions do not meet the need of performance to operate online and not allow scaling with the increase in the number of measurement channel. That is why an innovative DPP architecture is proposed in this paper. This architecture is able to overcome dead-time while being programmable and is flexible with the number of measurement channel. Proposed architecture is based on an innovative execution model for pulse processing applications which can be summarized as follow. The signal is not composed of pulses only, consequently, pulses processing does not have to operate on the entire signal. Therefore, the first step of our proposal is pulse extraction by the use of dedicated components named pulse extractors. The triggering step can be achieved after the analog-to-digital conversion without any signal shaping or filtering stages. Pileup detection and accurate pulse time stamping are done at this stage. Any application downstream this step can work on adaptive variable-sized array of samples simplifying pulse processing methods. Then, once the data flow is broken, it is possible to distribute pulses on Functional Units (FUs) which perform processing. As the date of each pulse is known, they can be processed individually out-of-order to provide the results. To manage the pulses distribution, a scheduler and an interconnection network are used. pulses are distributed on the first FU which is not busy without congesting the interconnection network. For this reason, the process duration does not result anymore in dead-time if there are enough FUs. FUs are designed to be standalone and to comprises at least a programmable general purpose processor (ARM, Microblaze) allowing the implementation of complex algorithms without any modification of the hardware. An acquisition chain is composed of a succession of algorithms which lead to organize our FUs as a software macro-pipeline, A simple approach consists in assigning one algorithm per FU. Consequently, the global latency becomes the worst latency of algorithms execution on FU. Moreover, as algorithms are executed locally - i.e. on a FU - this approach limits shared memory requirement. To handle multichannel, we propose FUs sharing, this approach maximize the chance to find a non-busy FU to process an incoming pulse. This is possible since each channel receive random event independently, the pulse extractors associated to them do not necessarily need to access simultaneously to all Computing resources at the same time to distribute their pulses. The major contribution of this paper is the proposition of an execution model and its associated hardware programmable architecture for digital pulse processing that can handle multiple acquisition channels while maintaining the scalability thanks to the use of shared resources. This execution model and associated architecture are validated by simulation of a cycle accurate architecture SystemC model. Proposed architecture shows promising results in terms of scalability while maintaining zero dead-time. This work also permit the sizing of hardware resources requirement required for a predefined set of applications. Future work will focus on the interconnection network and a scheduling policy that can exploit the variable-length of pulses. Then, the hardware implementation of this architecture will be performed and tested for a representative set of application.« less

A smart-pixel holographic competitive learning network

NASA Astrophysics Data System (ADS)

Slagle, Timothy Michael

Neural networks are adaptive classifiers which modify their decision boundaries based on feedback from externally- or internally-generated error signals. Optics is an attractive technology for neural network implementation because it offers the possibility of parallel, nearly instantaneous computation of the weighted neuron inputs by the propagation of light through the optical system. Using current optical device technology, system performance levels of 3 × 1011 connection updates per second can be achieved. This thesis presents an architecture for an optical competitive learning network which offers advantages over previous optical implementations, including smart-pixel-based optical neurons, phase- conjugate self-alignment of a single neuron plane, and high-density, parallel-access weight storage, interconnection, and learning in a volume hologram. The competitive learning algorithm with modifications for optical implementation is described, and algorithm simulations are performed for an example problem. The optical competitive learning architecture is then introduced. The optical system is simulated using the ``beamprop'' algorithm at the level of light propagating through the system components, and results showing competitive learning operation in agreement with the algorithm simulations are presented. The optical competitive learning requires a non-linear, non-local ``winner-take-all'' (WTA) neuron function. Custom-designed smart-pixel WTA neuron arrays were fabricated using CMOS VLSI/liquid crystal technology. Results of laboratory tests of the WTA arrays' switching characteristics, time response, and uniformity are then presented. The system uses a phase-conjugate mirror to write the self-aligning interconnection weight holograms, and energy gain is required from the reflection to minimize erasure of the existing weights. An experimental system for characterizing the PCM response is described. Useful gains of 20 were obtained with a polarization-multiplexed PCM readout, and gains of up to 60 were observed when a time-sequential read-out technique was used. Finally, the optical competitive learning laboratory system is described, including some necessary modifications to the previous architectures, and the data acquisition and control system developed for the system. Experimental results showing phase conjugation of the WTA outputs, holographic interconnect storage, associative storage between input images and WTA neuron outputs, and WTA array switching are presented, demonstrating the functions necessary for the operation of the optical learning system.

FPGA-accelerated algorithm for the regular expression matching system

NASA Astrophysics Data System (ADS)

Russek, P.; Wiatr, K.

2015-01-01

This article describes an algorithm to support a regular expressions matching system. The goal was to achieve an attractive performance system with low energy consumption. The basic idea of the algorithm comes from a concept of the Bloom filter. It starts from the extraction of static sub-strings for strings of regular expressions. The algorithm is devised to gain from its decomposition into parts which are intended to be executed by custom hardware and the central processing unit (CPU). The pipelined custom processor architecture is proposed and a software algorithm explained accordingly. The software part of the algorithm was coded in C and runs on a processor from the ARM family. The hardware architecture was described in VHDL and implemented in field programmable gate array (FPGA). The performance results and required resources of the above experiments are given. An example of target application for the presented solution is computer and network security systems. The idea was tested on nearly 100,000 body-based viruses from the ClamAV virus database. The solution is intended for the emerging technology of clusters of low-energy computing nodes.

Inference of scale-free networks from gene expression time series.

PubMed

Daisuke, Tominaga; Horton, Paul

2006-04-01

Quantitative time-series observation of gene expression is becoming possible, for example by cell array technology. However, there are no practical methods with which to infer network structures using only observed time-series data. As most computational models of biological networks for continuous time-series data have a high degree of freedom, it is almost impossible to infer the correct structures. On the other hand, it has been reported that some kinds of biological networks, such as gene networks and metabolic pathways, may have scale-free properties. We hypothesize that the architecture of inferred biological network models can be restricted to scale-free networks. We developed an inference algorithm for biological networks using only time-series data by introducing such a restriction. We adopt the S-system as the network model, and a distributed genetic algorithm to optimize models to fit its simulated results to observed time series data. We have tested our algorithm on a case study (simulated data). We compared optimization under no restriction, which allows for a fully connected network, and under the restriction that the total number of links must equal that expected from a scale free network. The restriction reduced both false positive and false negative estimation of the links and also the differences between model simulation and the given time-series data.

Artificial Neural Networks for differential diagnosis of breast lesions in MR-Mammography: a systematic approach addressing the influence of network architecture on diagnostic performance using a large clinical database.

PubMed

Dietzel, Matthias; Baltzer, Pascal A T; Dietzel, Andreas; Zoubi, Ramy; Gröschel, Tobias; Burmeister, Hartmut P; Bogdan, Martin; Kaiser, Werner A

2012-07-01

Differential diagnosis of lesions in MR-Mammography (MRM) remains a complex task. The aim of this MRM study was to design and to test robustness of Artificial Neural Network architectures to predict malignancy using a large clinical database. For this IRB-approved investigation standardized protocols and study design were applied (T1w-FLASH; 0.1 mmol/kgBW Gd-DTPA; T2w-TSE; histological verification after MRM). All lesions were evaluated by two experienced (>500 MRM) radiologists in consensus. In every lesion, 18 previously published descriptors were assessed and documented in the database. An Artificial Neural Network (ANN) was developed to process this database (The-MathWorks/Inc., feed-forward-architecture/resilient back-propagation-algorithm). All 18 descriptors were set as input variables, whereas histological results (malignant vs. benign) was defined as classification variable. Initially, the ANN was optimized in terms of "Training Epochs" (TE), "Hidden Layers" (HL), "Learning Rate" (LR) and "Neurons" (N). Robustness of the ANN was addressed by repeated evaluation cycles (n: 9) with receiver operating characteristics (ROC) analysis of the results applying 4-fold Cross Validation. The best network architecture was identified comparing the corresponding Area under the ROC curve (AUC). Histopathology revealed 436 benign and 648 malignant lesions. Enhancing the level of complexity could not increase diagnostic accuracy of the network (P: n.s.). The optimized ANN architecture (TE: 20, HL: 1, N: 5, LR: 1.2) was accurate (mean-AUC 0.888; P: <0.001) and robust (CI: 0.885-0.892; range: 0.880-0.898). The optimized neural network showed robust performance and high diagnostic accuracy for prediction of malignancy on unknown data. Copyright © 2011 Elsevier Ireland Ltd. All rights reserved.

Learning in Artificial Neural Systems

NASA Technical Reports Server (NTRS)

Matheus, Christopher J.; Hohensee, William E.

1987-01-01

This paper presents an overview and analysis of learning in Artificial Neural Systems (ANS's). It begins with a general introduction to neural networks and connectionist approaches to information processing. The basis for learning in ANS's is then described, and compared with classical Machine learning. While similar in some ways, ANS learning deviates from tradition in its dependence on the modification of individual weights to bring about changes in a knowledge representation distributed across connections in a network. This unique form of learning is analyzed from two aspects: the selection of an appropriate network architecture for representing the problem, and the choice of a suitable learning rule capable of reproducing the desired function within the given network. The various network architectures are classified, and then identified with explicit restrictions on the types of functions they are capable of representing. The learning rules, i.e., algorithms that specify how the network weights are modified, are similarly taxonomized, and where possible, the limitations inherent to specific classes of rules are outlined.

A convolutional neural network neutrino event classifier

DOE PAGES

Aurisano, A.; Radovic, A.; Rocco, D.; ...

2016-09-01

Here, convolutional neural networks (CNNs) have been widely applied in the computer vision community to solve complex problems in image recognition and analysis. We describe an application of the CNN technology to the problem of identifying particle interactions in sampling calorimeters used commonly in high energy physics and high energy neutrino physics in particular. Following a discussion of the core concepts of CNNs and recent innovations in CNN architectures related to the field of deep learning, we outline a specific application to the NOvA neutrino detector. This algorithm, CVN (Convolutional Visual Network) identifies neutrino interactions based on their topology withoutmore » the need for detailed reconstruction and outperforms algorithms currently in use by the NOvA collaboration.« less

A convolutional neural network neutrino event classifier

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

Aurisano, A.; Radovic, A.; Rocco, D.

Here, convolutional neural networks (CNNs) have been widely applied in the computer vision community to solve complex problems in image recognition and analysis. We describe an application of the CNN technology to the problem of identifying particle interactions in sampling calorimeters used commonly in high energy physics and high energy neutrino physics in particular. Following a discussion of the core concepts of CNNs and recent innovations in CNN architectures related to the field of deep learning, we outline a specific application to the NOvA neutrino detector. This algorithm, CVN (Convolutional Visual Network) identifies neutrino interactions based on their topology withoutmore » the need for detailed reconstruction and outperforms algorithms currently in use by the NOvA collaboration.« less

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.

Virtual management of radiology examinations in the virtual radiology environment using common object request broker architecture services.

PubMed

Martinez, R; Rozenblit, J; Cook, J F; Chacko, A K; Timboe, H L

1999-05-01

In the Department of Defense (DoD), US Army Medical Command is now embarking on an extremely exciting new project--creating a virtual radiology environment (VRE) for the management of radiology examinations. The business of radiology in the military is therefore being reengineered on several fronts by the VRE Project. In the VRE Project, a set of intelligent agent algorithms determine where examinations are to routed for reading bases on a knowledge base of the entire VRE. The set of algorithms, called the Meta-Manager, is hierarchical and uses object-based communications between medical treatment facilities (MTFs) and medical centers that have digital imaging network picture archiving and communications systems (DIN-PACS) networks. The communications is based on use of common object request broker architecture (CORBA) objects and services to send patient demographics and examination images from DIN-PACS networks in the MTFs to the DIN-PACS networks at the medical centers for diagnosis. The Meta-Manager is also responsible for updating the diagnosis at the originating MTF. CORBA services are used to perform secure message communications between DIN-PACS nodes in the VRE network. The Meta-Manager has a fail-safe architecture that allows the master Meta-Manager function to float to regional Meta-Manager sites in case of server failure. A prototype of the CORBA-based Meta-Manager is being developed by the University of Arizona's Computer Engineering Research Laboratory using the unified modeling language (UML) as a design tool. The prototype will implement the main functions described in the Meta-Manager design specification. The results of this project are expected to reengineer the process of radiology in the military and have extensions to commercial radiology environments.

Neural network modelling of planform geometry of headland-bay beaches

NASA Astrophysics Data System (ADS)

Iglesias, G.; López, I.; Castro, A.; Carballo, R.

2009-02-01

The shoreline of beaches in the lee of coastal salients or man-made structures, usually known as headland-bay beaches, has a distinctive curvature; wave fronts curve as a result of wave diffraction at the headland and in turn cause the shoreline to bend. The ensuing curved planform is of great interest both as a peculiar landform and in the context of engineering projects in which it is necessary to predict how a coastal structure will affect the sandy shoreline in its lee. A number of empirical models have been put forward, each based on a specific equation. A novel approach, based on the application of artificial neural networks, is presented in this work. Unlike the conventional method, no particular equation of the planform is embedded in the model. Instead, it is the model itself that learns about the problem from a series of examples of headland-bay beaches (the training set) and thereafter applies this self-acquired knowledge to other cases (the test set) for validation. Twenty-three headland-bay beaches from around the world were selected, of which sixteen and seven make up the training and test sets, respectively. As there is no well-developed theory for deciding upon the most convenient neural network architecture to deal with a particular data set, an experimental study was conducted in which ten different architectures with one and two hidden neuron layers and five training algorithms - 50 different options combining network architecture and training algorithm - were compared. Each of these options was implemented, trained and tested in order to find the best-performing approach for modelling the planform of headland-bay beaches. Finally, the selected neural network model was compared with a state-of-the-art planform model and was shown to outperform it.

Efficient Sorting on the Tilera Manycore Architecture

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

Morari, Alessandro; Tumeo, Antonino; Villa, Oreste

e present an efficient implementation of the radix sort algo- rithm for the Tilera TILEPro64 processor. The TILEPro64 is one of the first successful commercial manycore processors. It is com- posed of 64 tiles interconnected through multiple fast Networks- on-chip and features a fully coherent, shared distributed cache. The architecture has a large degree of flexibility, and allows various optimization strategies. We describe how we mapped the algorithm to this architecture. We present an in-depth analysis of the optimizations for each phase of the algorithm with respect to the processor’s sustained performance. We discuss the overall throughput reached by ourmore » radix sort implementation (up to 132 MK/s) and show that it provides comparable or better performance-per-watt with respect to state-of-the art implemen- tations on x86 processors and graphic processing units.« less

Fuzzy Logic Module of Convolutional Neural Network for Handwritten Digits Recognition

NASA Astrophysics Data System (ADS)

Popko, E. A.; Weinstein, I. A.

2016-08-01

Optical character recognition is one of the important issues in the field of pattern recognition. This paper presents a method for recognizing handwritten digits based on the modeling of convolutional neural network. The integrated fuzzy logic module based on a structural approach was developed. Used system architecture adjusted the output of the neural network to improve quality of symbol identification. It was shown that proposed algorithm was flexible and high recognition rate of 99.23% was achieved.

Multilayer Statistical Intrusion Detection in Wireless Networks

NASA Astrophysics Data System (ADS)

Hamdi, Mohamed; Meddeb-Makhlouf, Amel; Boudriga, Noureddine

2008-12-01

The rapid proliferation of mobile applications and services has introduced new vulnerabilities that do not exist in fixed wired networks. Traditional security mechanisms, such as access control and encryption, turn out to be inefficient in modern wireless networks. Given the shortcomings of the protection mechanisms, an important research focuses in intrusion detection systems (IDSs). This paper proposes a multilayer statistical intrusion detection framework for wireless networks. The architecture is adequate to wireless networks because the underlying detection models rely on radio parameters and traffic models. Accurate correlation between radio and traffic anomalies allows enhancing the efficiency of the IDS. A radio signal fingerprinting technique based on the maximal overlap discrete wavelet transform (MODWT) is developed. Moreover, a geometric clustering algorithm is presented. Depending on the characteristics of the fingerprinting technique, the clustering algorithm permits to control the false positive and false negative rates. Finally, simulation experiments have been carried out to validate the proposed IDS.

Providing end-to-end QoS for multimedia applications in 3G wireless networks

NASA Astrophysics Data System (ADS)

Guo, Katherine; Rangarajan, Samapth; Siddiqui, M. A.; Paul, Sanjoy

2003-11-01

As the usage of wireless packet data services increases, wireless carriers today are faced with the challenge of offering multimedia applications with QoS requirements within current 3G data networks. End-to-end QoS requires support at the application, network, link and medium access control (MAC) layers. We discuss existing CDMA2000 network architecture and show its shortcomings that prevent supporting multiple classes of traffic at the Radio Access Network (RAN). We then propose changes in RAN within the standards framework that enable support for multiple traffic classes. In addition, we discuss how Session Initiation Protocol (SIP) can be augmented with QoS signaling for supporting end-to-end QoS. We also review state of the art scheduling algorithms at the base station and provide possible extensions to these algorithms to support different classes of traffic as well as different classes of users.

Informatics methods to enable sharing of quantitative imaging research data.

PubMed

Levy, Mia A; Freymann, John B; Kirby, Justin S; Fedorov, Andriy; Fennessy, Fiona M; Eschrich, Steven A; Berglund, Anders E; Fenstermacher, David A; Tan, Yongqiang; Guo, Xiaotao; Casavant, Thomas L; Brown, Bartley J; Braun, Terry A; Dekker, Andre; Roelofs, Erik; Mountz, James M; Boada, Fernando; Laymon, Charles; Oborski, Matt; Rubin, Daniel L

2012-11-01

The National Cancer Institute Quantitative Research Network (QIN) is a collaborative research network whose goal is to share data, algorithms and research tools to accelerate quantitative imaging research. A challenge is the variability in tools and analysis platforms used in quantitative imaging. Our goal was to understand the extent of this variation and to develop an approach to enable sharing data and to promote reuse of quantitative imaging data in the community. We performed a survey of the current tools in use by the QIN member sites for representation and storage of their QIN research data including images, image meta-data and clinical data. We identified existing systems and standards for data sharing and their gaps for the QIN use case. We then proposed a system architecture to enable data sharing and collaborative experimentation within the QIN. There are a variety of tools currently used by each QIN institution. We developed a general information system architecture to support the QIN goals. We also describe the remaining architecture gaps we are developing to enable members to share research images and image meta-data across the network. As a research network, the QIN will stimulate quantitative imaging research by pooling data, algorithms and research tools. However, there are gaps in current functional requirements that will need to be met by future informatics development. Special attention must be given to the technical requirements needed to translate these methods into the clinical research workflow to enable validation and qualification of these novel imaging biomarkers. Copyright © 2012 Elsevier Inc. All rights reserved.

The science of computing - Parallel computation

NASA Technical Reports Server (NTRS)

Denning, P. J.

1985-01-01

Although parallel computation architectures have been known for computers since the 1920s, it was only in the 1970s that microelectronic components technologies advanced to the point where it became feasible to incorporate multiple processors in one machine. Concommitantly, the development of algorithms for parallel processing also lagged due to hardware limitations. The speed of computing with solid-state chips is limited by gate switching delays. The physical limit implies that a 1 Gflop operational speed is the maximum for sequential processors. A computer recently introduced features a 'hypercube' architecture with 128 processors connected in networks at 5, 6 or 7 points per grid, depending on the design choice. Its computing speed rivals that of supercomputers, but at a fraction of the cost. The added speed with less hardware is due to parallel processing, which utilizes algorithms representing different parts of an equation that can be broken into simpler statements and processed simultaneously. Present, highly developed computer languages like FORTRAN, PASCAL, COBOL, etc., rely on sequential instructions. Thus, increased emphasis will now be directed at parallel processing algorithms to exploit the new architectures.

MoNET: media over net gateway processor for next-generation network

NASA Astrophysics Data System (ADS)

Elabd, Hammam; Sundar, Rangarajan; Dedes, John

2001-12-01

MoNETTM (Media over Net) SX000 product family is designed using a scalable voice, video and packet-processing platform to address applications with channel densities from few voice channels to four OC3 per card. This platform is developed for bridging public circuit-switched network to the next generation packet telephony and data network. The platform consists of a DSP farm, RISC processors and interface modules. DSP farm is required to execute voice compression, image compression and line echo cancellation algorithms for large number of voice, video, fax, and modem or data channels. RISC CPUs are used for performing various packetizations based on RTP, UDP/IP and ATM encapsulations. In addition, RISC CPUs also participate in the DSP farm load management and communication with the host and other MoP devices. The MoNETTM S1000 communications device is designed for voice processing and for bridging TDM to ATM and IP packet networks. The S1000 consists of the DSP farm based on Carmel DSP core and 32-bit RISC CPU, along with Ethernet, Utopia, PCI, and TDM interfaces. In this paper, we will describe the VoIP infrastructure, building blocks of the S500, S1000 and S3000 devices, algorithms executed on these device and associated channel densities, detailed DSP architecture, memory architecture, data flow and scheduling.

Key on demand (KoD) for software-defined optical networks secured by quantum key distribution (QKD).

PubMed

Cao, Yuan; Zhao, Yongli; Colman-Meixner, Carlos; Yu, Xiaosong; Zhang, Jie

2017-10-30

Software-defined optical networking (SDON) will become the next generation optical network architecture. However, the optical layer and control layer of SDON are vulnerable to cyberattacks. While, data encryption is an effective method to minimize the negative effects of cyberattacks, secure key interchange is its major challenge which can be addressed by the quantum key distribution (QKD) technique. Hence, in this paper we discuss the integration of QKD with WDM optical networks to secure the SDON architecture by introducing a novel key on demand (KoD) scheme which is enabled by a novel routing, wavelength and key assignment (RWKA) algorithm. The QKD over SDON with KoD model follows two steps to provide security: i) quantum key pools (QKPs) construction for securing the control channels (CChs) and data channels (DChs); ii) the KoD scheme uses RWKA algorithm to allocate and update secret keys for different security requirements. To test our model, we define a security probability index which measures the security gain in CChs and DChs. Simulation results indicate that the security performance of CChs and DChs can be enhanced by provisioning sufficient secret keys in QKPs and performing key-updating considering potential cyberattacks. Also, KoD is beneficial to achieve a positive balance between security requirements and key resource usage.

Air Pollution Monitoring and Mining Based on Sensor Grid in London

PubMed Central

Ma, Yajie; Richards, Mark; Ghanem, Moustafa; Guo, Yike; Hassard, John

2008-01-01

In this paper, we present a distributed infrastructure based on wireless sensors network and Grid computing technology for air pollution monitoring and mining, which aims to develop low-cost and ubiquitous sensor networks to collect real-time, large scale and comprehensive environmental data from road traffic emissions for air pollution monitoring in urban environment. The main informatics challenges in respect to constructing the high-throughput sensor Grid are discussed in this paper. We present a two-layer network framework, a P2P e-Science Grid architecture, and the distributed data mining algorithm as the solutions to address the challenges. We simulated the system in TinyOS to examine the operation of each sensor as well as the networking performance. We also present the distributed data mining result to examine the effectiveness of the algorithm. PMID:27879895

Air Pollution Monitoring and Mining Based on Sensor Grid in London.

PubMed

Ma, Yajie; Richards, Mark; Ghanem, Moustafa; Guo, Yike; Hassard, John

2008-06-01

In this paper, we present a distributed infrastructure based on wireless sensors network and Grid computing technology for air pollution monitoring and mining, which aims to develop low-cost and ubiquitous sensor networks to collect real-time, large scale and comprehensive environmental data from road traffic emissions for air pollution monitoring in urban environment. The main informatics challenges in respect to constructing the high-throughput sensor Grid are discussed in this paper. We present a twolayer network framework, a P2P e-Science Grid architecture, and the distributed data mining algorithm as the solutions to address the challenges. We simulated the system in TinyOS to examine the operation of each sensor as well as the networking performance. We also present the distributed data mining result to examine the effectiveness of the algorithm.

A 181 GOPS AKAZE Accelerator Employing Discrete-Time Cellular Neural Networks for Real-Time Feature Extraction.

PubMed

Jiang, Guangli; Liu, Leibo; Zhu, Wenping; Yin, Shouyi; Wei, Shaojun

2015-09-04

This paper proposes a real-time feature extraction VLSI architecture for high-resolution images based on the accelerated KAZE algorithm. Firstly, a new system architecture is proposed. It increases the system throughput, provides flexibility in image resolution, and offers trade-offs between speed and scaling robustness. The architecture consists of a two-dimensional pipeline array that fully utilizes computational similarities in octaves. Secondly, a substructure (block-serial discrete-time cellular neural network) that can realize a nonlinear filter is proposed. This structure decreases the memory demand through the removal of data dependency. Thirdly, a hardware-friendly descriptor is introduced in order to overcome the hardware design bottleneck through the polar sample pattern; a simplified method to realize rotation invariance is also presented. Finally, the proposed architecture is designed in TSMC 65 nm CMOS technology. The experimental results show a performance of 127 fps in full HD resolution at 200 MHz frequency. The peak performance reaches 181 GOPS and the throughput is double the speed of other state-of-the-art architectures.

Geometrical structure of Neural Networks: Geodesics, Jeffrey's Prior and Hyper-ribbons

NASA Astrophysics Data System (ADS)

Hayden, Lorien; Alemi, Alex; Sethna, James

2014-03-01

Neural networks are learning algorithms which are employed in a host of Machine Learning problems including speech recognition, object classification and data mining. In practice, neural networks learn a low dimensional representation of high dimensional data and define a model manifold which is an embedding of this low dimensional structure in the higher dimensional space. In this work, we explore the geometrical structure of a neural network model manifold. A Stacked Denoising Autoencoder and a Deep Belief Network are trained on handwritten digits from the MNIST database. Construction of geodesics along the surface and of slices taken from the high dimensional manifolds reveal a hierarchy of widths corresponding to a hyper-ribbon structure. This property indicates that neural networks fall into the class of sloppy models, in which certain parameter combinations dominate the behavior. Employing this information could prove valuable in designing both neural network architectures and training algorithms. This material is based upon work supported by the National Science Foundation Graduate Research Fellowship under Grant No . DGE-1144153.

Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction.

PubMed

Ma, Xiaolei; Dai, Zhuang; He, Zhengbing; Ma, Jihui; Wang, Yong; Wang, Yunpeng

2017-04-10

This paper proposes a convolutional neural network (CNN)-based method that learns traffic as images and predicts large-scale, network-wide traffic speed with a high accuracy. Spatiotemporal traffic dynamics are converted to images describing the time and space relations of traffic flow via a two-dimensional time-space matrix. A CNN is applied to the image following two consecutive steps: abstract traffic feature extraction and network-wide traffic speed prediction. The effectiveness of the proposed method is evaluated by taking two real-world transportation networks, the second ring road and north-east transportation network in Beijing, as examples, and comparing the method with four prevailing algorithms, namely, ordinary least squares, k-nearest neighbors, artificial neural network, and random forest, and three deep learning architectures, namely, stacked autoencoder, recurrent neural network, and long-short-term memory network. The results show that the proposed method outperforms other algorithms by an average accuracy improvement of 42.91% within an acceptable execution time. The CNN can train the model in a reasonable time and, thus, is suitable for large-scale transportation networks.

Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction

PubMed Central

Ma, Xiaolei; Dai, Zhuang; He, Zhengbing; Ma, Jihui; Wang, Yong; Wang, Yunpeng

2017-01-01

This paper proposes a convolutional neural network (CNN)-based method that learns traffic as images and predicts large-scale, network-wide traffic speed with a high accuracy. Spatiotemporal traffic dynamics are converted to images describing the time and space relations of traffic flow via a two-dimensional time-space matrix. A CNN is applied to the image following two consecutive steps: abstract traffic feature extraction and network-wide traffic speed prediction. The effectiveness of the proposed method is evaluated by taking two real-world transportation networks, the second ring road and north-east transportation network in Beijing, as examples, and comparing the method with four prevailing algorithms, namely, ordinary least squares, k-nearest neighbors, artificial neural network, and random forest, and three deep learning architectures, namely, stacked autoencoder, recurrent neural network, and long-short-term memory network. The results show that the proposed method outperforms other algorithms by an average accuracy improvement of 42.91% within an acceptable execution time. The CNN can train the model in a reasonable time and, thus, is suitable for large-scale transportation networks. PMID:28394270

Implementation theory of distortion-invariant pattern recognition for optical and digital signal processing systems

NASA Astrophysics Data System (ADS)

Lhamon, Michael Earl

A pattern recognition system which uses complex correlation filter banks requires proportionally more computational effort than single-real valued filters. This introduces increased computation burden but also introduces a higher level of parallelism, that common computing platforms fail to identify. As a result, we consider algorithm mapping to both optical and digital processors. For digital implementation, we develop computationally efficient pattern recognition algorithms, referred to as, vector inner product operators that require less computational effort than traditional fast Fourier methods. These algorithms do not need correlation and they map readily onto parallel digital architectures, which imply new architectures for optical processors. These filters exploit circulant-symmetric matrix structures of the training set data representing a variety of distortions. By using the same mathematical basis as with the vector inner product operations, we are able to extend the capabilities of more traditional correlation filtering to what we refer to as "Super Images". These "Super Images" are used to morphologically transform a complicated input scene into a predetermined dot pattern. The orientation of the dot pattern is related to the rotational distortion of the object of interest. The optical implementation of "Super Images" yields feature reduction necessary for using other techniques, such as artificial neural networks. We propose a parallel digital signal processor architecture based on specific pattern recognition algorithms but general enough to be applicable to other similar problems. Such an architecture is classified as a data flow architecture. Instead of mapping an algorithm to an architecture, we propose mapping the DSP architecture to a class of pattern recognition algorithms. Today's optical processing systems have difficulties implementing full complex filter structures. Typically, optical systems (like the 4f correlators) are limited to phase-only implementation with lower detection performance than full complex electronic systems. Our study includes pseudo-random pixel encoding techniques for approximating full complex filtering. Optical filter bank implementation is possible and they have the advantage of time averaging the entire filter bank at real time rates. Time-averaged optical filtering is computational comparable to billions of digital operations-per-second. For this reason, we believe future trends in high speed pattern recognition will involve hybrid architectures of both optical and DSP elements.

A flexible data fusion architecture for persistent surveillance using ultra-low-power wireless sensor networks

NASA Astrophysics Data System (ADS)

Hanson, Jeffrey A.; McLaughlin, Keith L.; Sereno, Thomas J.

2011-06-01

We have developed a flexible, target-driven, multi-modal, physics-based fusion architecture that efficiently searches sensor detections for targets and rejects clutter while controlling the combinatoric problems that commonly arise in datadriven fusion systems. The informational constraints imposed by long lifetime requirements make systems vulnerable to false alarms. We demonstrate that our data fusion system significantly reduces false alarms while maintaining high sensitivity to threats. In addition, mission goals can vary substantially in terms of targets-of-interest, required characterization, acceptable latency, and false alarm rates. Our fusion architecture provides the flexibility to match these trade-offs with mission requirements unlike many conventional systems that require significant modifications for each new mission. We illustrate our data fusion performance with case studies that span many of the potential mission scenarios including border surveillance, base security, and infrastructure protection. In these studies, we deployed multi-modal sensor nodes - including geophones, magnetometers, accelerometers and PIR sensors - with low-power processing algorithms and low-bandwidth wireless mesh networking to create networks capable of multi-year operation. The results show our data fusion architecture maintains high sensitivities while suppressing most false alarms for a variety of environments and targets.

Hybrid power system intelligent operation and protection involving distributed architectures and pulsed loads

NASA Astrophysics Data System (ADS)

Mohamed, Ahmed

Efficient and reliable techniques for power delivery and utilization are needed to account for the increased penetration of renewable energy sources in electric power systems. Such methods are also required for current and future demands of plug-in electric vehicles and high-power electronic loads. Distributed control and optimal power network architectures will lead to viable solutions to the energy management issue with high level of reliability and security. This dissertation is aimed at developing and verifying new techniques for distributed control by deploying DC microgrids, involving distributed renewable generation and energy storage, through the operating AC power system. To achieve the findings of this dissertation, an energy system architecture was developed involving AC and DC networks, both with distributed generations and demands. The various components of the DC microgrid were designed and built including DC-DC converters, voltage source inverters (VSI) and AC-DC rectifiers featuring novel designs developed by the candidate. New control techniques were developed and implemented to maximize the operating range of the power conditioning units used for integrating renewable energy into the DC bus. The control and operation of the DC microgrids in the hybrid AC/DC system involve intelligent energy management. Real-time energy management algorithms were developed and experimentally verified. These algorithms are based on intelligent decision-making elements along with an optimization process. This was aimed at enhancing the overall performance of the power system and mitigating the effect of heavy non-linear loads with variable intensity and duration. The developed algorithms were also used for managing the charging/discharging process of plug-in electric vehicle emulators. The protection of the proposed hybrid AC/DC power system was studied. Fault analysis and protection scheme and coordination, in addition to ideas on how to retrofit currently available protection concepts and devices for AC systems in a DC network, were presented. A study was also conducted on the effect of changing the distribution architecture and distributing the storage assets on the various zones of the network on the system's dynamic security and stability. A practical shipboard power system was studied as an example of a hybrid AC/DC power system involving pulsed loads. Generally, the proposed hybrid AC/DC power system, besides most of the ideas, controls and algorithms presented in this dissertation, were experimentally verified at the Smart Grid Testbed, Energy Systems Research Laboratory. All the developments in this dissertation were experimentally verified at the Smart Grid Testbed.

Melanoma segmentation based on deep learning.

PubMed

Zhang, Xiaoqing

2017-12-01

Malignant melanoma is one of the most deadly forms of skin cancer, which is one of the world's fastest-growing cancers. Early diagnosis and treatment is critical. In this study, a neural network structure is utilized to construct a broad and accurate basis for the diagnosis of skin cancer, thereby reducing screening errors. The technique is able to improve the efficacy for identification of normally indistinguishable lesions (such as pigment spots) versus clinically unknown lesions, and to ultimately improve the diagnostic accuracy. In the field of medical imaging, in general, using neural networks for image segmentation is relatively rare. The existing traditional machine-learning neural network algorithms still cannot completely solve the problem of information loss, nor detect the precise division of the boundary area. We use an improved neural network framework, described herein, to achieve efficacious feature learning, and satisfactory segmentation of melanoma images. The architecture of the network includes multiple convolution layers, dropout layers, softmax layers, multiple filters, and activation functions. The number of data sets can be increased via rotation of the training set. A non-linear activation function (such as ReLU and ELU) is employed to alleviate the problem of gradient disappearance, and RMSprop/Adam are incorporated to optimize the loss algorithm. A batch normalization layer is added between the convolution layer and the activation layer to solve the problem of gradient disappearance and explosion. Experiments, described herein, show that our improved neural network architecture achieves higher accuracy for segmentation of melanoma images as compared with existing processes.

Thermalnet: a Deep Convolutional Network for Synthetic Thermal Image Generation

NASA Astrophysics Data System (ADS)

Kniaz, V. V.; Gorbatsevich, V. S.; Mizginov, V. A.

2017-05-01

Deep convolutional neural networks have dramatically changed the landscape of the modern computer vision. Nowadays methods based on deep neural networks show the best performance among image recognition and object detection algorithms. While polishing of network architectures received a lot of scholar attention, from the practical point of view the preparation of a large image dataset for a successful training of a neural network became one of major challenges. This challenge is particularly profound for image recognition in wavelengths lying outside the visible spectrum. For example no infrared or radar image datasets large enough for successful training of a deep neural network are available to date in public domain. Recent advances of deep neural networks prove that they are also capable to do arbitrary image transformations such as super-resolution image generation, grayscale image colorisation and imitation of style of a given artist. Thus a natural question arise: how could be deep neural networks used for augmentation of existing large image datasets? This paper is focused on the development of the Thermalnet deep convolutional neural network for augmentation of existing large visible image datasets with synthetic thermal images. The Thermalnet network architecture is inspired by colorisation deep neural networks.

Sparse matrix-vector multiplication on network-on-chip

NASA Astrophysics Data System (ADS)

Sun, C.-C.; Götze, J.; Jheng, H.-Y.; Ruan, S.-J.

2010-12-01

In this paper, we present an idea for performing matrix-vector multiplication by using Network-on-Chip (NoC) architecture. In traditional IC design on-chip communications have been designed with dedicated point-to-point interconnections. Therefore, regular local data transfer is the major concept of many parallel implementations. However, when dealing with the parallel implementation of sparse matrix-vector multiplication (SMVM), which is the main step of all iterative algorithms for solving systems of linear equation, the required data transfers depend on the sparsity structure of the matrix and can be extremely irregular. Using the NoC architecture makes it possible to deal with arbitrary structure of the data transfers; i.e. with the irregular structure of the sparse matrices. So far, we have already implemented the proposed SMVM-NoC architecture with the size 4×4 and 5×5 in IEEE 754 single float point precision using FPGA.

UAV Cooperation Architectures for Persistent Sensing

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

Roberts, R S; Kent, C A; Jones, E D

2003-03-20

With the number of small, inexpensive Unmanned Air Vehicles (UAVs) increasing, it is feasible to build multi-UAV sensing networks. In particular, by using UAVs in conjunction with unattended ground sensors, a degree of persistent sensing can be achieved. With proper UAV cooperation algorithms, sensing is maintained even though exceptional events, e.g., the loss of a UAV, have occurred. In this paper a cooperation technique that allows multiple UAVs to perform coordinated, persistent sensing with unattended ground sensors over a wide area is described. The technique automatically adapts the UAV paths so that on the average, the amount of time thatmore » any sensor has to wait for a UAV revisit is minimized. We also describe the Simulation, Tactical Operations and Mission Planning (STOMP) software architecture. This architecture is designed to help simulate and operate distributed sensor networks where multiple UAVs are used to collect data.« less

The emergence of overlapping scale-free genetic architecture in digital organisms.

PubMed

Gerlee, P; Lundh, T

2008-01-01

We have studied the evolution of genetic architecture in digital organisms and found that the gene overlap follows a scale-free distribution, which is commonly found in metabolic networks of many organisms. Our results show that the slope of the scale-free distribution depends on the mutation rate and that the gene development is driven by expansion of already existing genes, which is in direct correspondence to the preferential growth algorithm that gives rise to scale-free networks. To further validate our results we have constructed a simple model of gene development, which recapitulates the results from the evolutionary process and shows that the mutation rate affects the tendency of genes to cluster. In addition we could relate the slope of the scale-free distribution to the genetic complexity of the organisms and show that a high mutation rate gives rise to a more complex genetic architecture.

Predicting Length of Stay in Intensive Care Units after Cardiac Surgery: Comparison of Artificial Neural Networks and Adaptive Neuro-fuzzy System.

PubMed

Maharlou, Hamidreza; Niakan Kalhori, Sharareh R; Shahbazi, Shahrbanoo; Ravangard, Ramin

2018-04-01

Accurate prediction of patients' length of stay is highly important. This study compared the performance of artificial neural network and adaptive neuro-fuzzy system algorithms to predict patients' length of stay in intensive care units (ICU) after cardiac surgery. A cross-sectional, analytical, and applied study was conducted. The required data were collected from 311 cardiac patients admitted to intensive care units after surgery at three hospitals of Shiraz, Iran, through a non-random convenience sampling method during the second quarter of 2016. Following the initial processing of influential factors, models were created and evaluated. The results showed that the adaptive neuro-fuzzy algorithm (with mean squared error [MSE] = 7 and R = 0.88) resulted in the creation of a more precise model than the artificial neural network (with MSE = 21 and R = 0.60). The adaptive neuro-fuzzy algorithm produces a more accurate model as it applies both the capabilities of a neural network architecture and experts' knowledge as a hybrid algorithm. It identifies nonlinear components, yielding remarkable results for prediction the length of stay, which is a useful calculation output to support ICU management, enabling higher quality of administration and cost reduction.

Learning in stochastic neural networks for constraint satisfaction problems

NASA Technical Reports Server (NTRS)

Johnston, Mark D.; Adorf, Hans-Martin

1989-01-01

Researchers describe a newly-developed artificial neural network algorithm for solving constraint satisfaction problems (CSPs) which includes a learning component that can significantly improve the performance of the network from run to run. The network, referred to as the Guarded Discrete Stochastic (GDS) network, is based on the discrete Hopfield network but differs from it primarily in that auxiliary networks (guards) are asymmetrically coupled to the main network to enforce certain types of constraints. Although the presence of asymmetric connections implies that the network may not converge, it was found that, for certain classes of problems, the network often quickly converges to find satisfactory solutions when they exist. The network can run efficiently on serial machines and can find solutions to very large problems (e.g., N-queens for N as large as 1024). One advantage of the network architecture is that network connection strengths need not be instantiated when the network is established: they are needed only when a participating neural element transitions from off to on. They have exploited this feature to devise a learning algorithm, based on consistency techniques for discrete CSPs, that updates the network biases and connection strengths and thus improves the network performance.

Holding-time-aware asymmetric spectrum allocation in virtual optical networks

NASA Astrophysics Data System (ADS)

Lyu, Chunjian; Li, Hui; Liu, Yuze; Ji, Yuefeng

2017-10-01

Virtual optical networks (VONs) have been considered as a promising solution to support current high-capacity dynamic traffic and achieve rapid applications deployment. Since most of the network services (e.g., high-definition video service, cloud computing, distributed storage) in VONs are provisioned by dedicated data centers, needing different amount of bandwidth resources in both directions, the network traffic is mostly asymmetric. The common strategy, symmetric provisioning of traffic in optical networks, leads to a waste of spectrum resources in such traffic patterns. In this paper, we design a holding-time-aware asymmetric spectrum allocation module based on SDON architecture and an asymmetric spectrum allocation algorithm based on the module is proposed. For the purpose of reducing spectrum resources' waste, the algorithm attempts to reallocate the idle unidirectional spectrum slots in VONs, which are generated due to the asymmetry of services' bidirectional bandwidth. This part of resources can be exploited by other requests, such as short-time non-VON requests. We also introduce a two-dimensional asymmetric resource model for maintaining idle spectrum resources information of VON in spectrum and time domains. Moreover, a simulation is designed to evaluate the performance of the proposed algorithm, and results show that our proposed asymmetric spectrum allocation algorithm can improve the resource waste and reduce blocking probability.

Cascaded VLSI neural network architecture for on-line learning

NASA Technical Reports Server (NTRS)

Thakoor, Anilkumar P. (Inventor); Duong, Tuan A. (Inventor); Daud, Taher (Inventor)

1992-01-01

High-speed, analog, fully-parallel, and asynchronous building blocks are cascaded for larger sizes and enhanced resolution. A hardware compatible algorithm permits hardware-in-the-loop learning despite limited weight resolution. A computation intensive feature classification application was demonstrated with this flexible hardware and new algorithm at high speed. This result indicates that these building block chips can be embedded as an application specific coprocessor for solving real world problems at extremely high data rates.

Cascaded VLSI neural network architecture for on-line learning

NASA Technical Reports Server (NTRS)

Duong, Tuan A. (Inventor); Daud, Taher (Inventor); Thakoor, Anilkumar P. (Inventor)

1995-01-01

High-speed, analog, fully-parallel and asynchronous building blocks are cascaded for larger sizes and enhanced resolution. A hardware-compatible algorithm permits hardware-in-the-loop learning despite limited weight resolution. A comparison-intensive feature classification application has been demonstrated with this flexible hardware and new algorithm at high speed. This result indicates that these building block chips can be embedded as application-specific-coprocessors for solving real-world problems at extremely high data rates.

Efficient Security Mechanisms for the Border Gateway Routing Protocol

DTIC Science & Technology

1997-08-22

Finding Algorithm for Loop- Free Routing. IEEE/ACM Transactions on Networking, 5(1):148{160, Feb. 1997. [7] International Standards Organization. ISO/IEC...Jersey 07974, Feb. 1985. ftp://netlib.att.com/netlib/att/cs/ cstr /117.ps.Z. [16] S. L. Murphy. Presentation in Panel on \\Security Architecture for the

Fuzzy control of magnetic bearings

NASA Technical Reports Server (NTRS)

Feeley, J. J.; Niederauer, G. M.; Ahlstrom, D. J.

1991-01-01

The use of an adaptive fuzzy control algorithm implemented on a VLSI chip for the control of a magnetic bearing was considered. The architecture of the adaptive fuzzy controller is similar to that of a neural network. The performance of the fuzzy controller is compared to that of a conventional controller by computer simulation.

Optimal Simulations by Butterfly Networks: Extended Abstract,

DTIC Science & Technology

1987-11-01

Typescript , Univ. of Massachusetts; submitted for nublication. 1_2.2 Ll, - W 12. ifliU 1.8 UI1.25 . l i I 61 MICROCOPY RESOLUTION TEST CHART NATIONAL...1987): An optimal mapping of the FFT algorithm onto the tlypercube architecture. Typescript , Univ. of Massachusetts; submitted for publication. (HR I

Systems and Algorithms for Automated Collaborative Observation Using Networked Robotic Cameras

ERIC Educational Resources Information Center

Xu, Yiliang

2011-01-01

The development of telerobotic systems has evolved from Single Operator Single Robot (SOSR) systems to Multiple Operator Multiple Robot (MOMR) systems. The relationship between human operators and robots follows the master-slave control architecture and the requests for controlling robot actuation are completely generated by human operators. …

Gradient descent learning algorithm overview: a general dynamical systems perspective.

PubMed

Baldi, P

1995-01-01

Gives a unified treatment of gradient descent learning algorithms for neural networks using a general framework of dynamical systems. This general approach organizes and simplifies all the known algorithms and results which have been originally derived for different problems (fixed point/trajectory learning), for different models (discrete/continuous), for different architectures (forward/recurrent), and using different techniques (backpropagation, variational calculus, adjoint methods, etc.). The general approach can also be applied to derive new algorithms. The author then briefly examines some of the complexity issues and limitations intrinsic to gradient descent learning. Throughout the paper, the author focuses on the problem of trajectory learning.

Historical data learning based dynamic LSP routing for overlay IP/MPLS over WDM networks

NASA Astrophysics Data System (ADS)

Yu, Xiaojun; Xiao, Gaoxi; Cheng, Tee Hiang

2013-08-01

Overlay IP/MPLS over WDM network is a promising network architecture starting to gain wide deployments recently. A desirable feature of such a network is to achieve efficient routing with limited information exchanges between the IP/MPLS and the WDM layers. This paper studies dynamic label switched path (LSP) routing in the overlay IP/MPLS over WDM networks. To enhance network performance while maintaining its simplicity, we propose to learn from the historical data of lightpath setup costs maintained by the IP-layer integrated service provider (ISP) when making routing decisions. Using a novel historical data learning scheme for logical link cost estimation, we develop a new dynamic LSP routing method named Existing Link First (ELF) algorithm. Simulation results show that the proposed algorithm significantly outperforms the existing ones under different traffic loads, with either limited or unlimited numbers of optical ports. Effects of the number of candidate routes, add/drop ratio and the amount of historical data are also evaluated.

Flexible architecture of data acquisition firmware based on multi-behaviors finite state machine

NASA Astrophysics Data System (ADS)

Arpaia, Pasquale; Cimmino, Pasquale

2016-11-01

A flexible firmware architecture for different kinds of data acquisition systems, ranging from high-precision bench instruments to low-cost wireless transducers networks, is presented. The key component is a multi-behaviors finite state machine, easily configurable to both low- and high-performance requirements, to diverse operating systems, as well as to on-line and batch measurement algorithms. The proposed solution was validated experimentally on three case studies with data acquisition architectures: (i) concentrated, in a high-precision instrument for magnetic measurements at CERN, (ii) decentralized, for telemedicine remote monitoring of patients at home, and (iii) distributed, for remote monitoring of building's energy loss.

Generalised Transfer Functions of Neural Networks

NASA Astrophysics Data System (ADS)

Fung, C. F.; Billings, S. A.; Zhang, H.

1997-11-01

When artificial neural networks are used to model non-linear dynamical systems, the system structure which can be extremely useful for analysis and design, is buried within the network architecture. In this paper, explicit expressions for the frequency response or generalised transfer functions of both feedforward and recurrent neural networks are derived in terms of the network weights. The derivation of the algorithm is established on the basis of the Taylor series expansion of the activation functions used in a particular neural network. This leads to a representation which is equivalent to the non-linear recursive polynomial model and enables the derivation of the transfer functions to be based on the harmonic expansion method. By mapping the neural network into the frequency domain information about the structure of the underlying non-linear system can be recovered. Numerical examples are included to demonstrate the application of the new algorithm. These examples show that the frequency response functions appear to be highly sensitive to the network topology and training, and that the time domain properties fail to reveal deficiencies in the trained network structure.

INFORM Lab: a testbed for high-level information fusion and resource management

NASA Astrophysics Data System (ADS)

Valin, Pierre; Guitouni, Adel; Bossé, Eloi; Wehn, Hans; Happe, Jens

2011-05-01

DRDC Valcartier and MDA have created an advanced simulation testbed for the purpose of evaluating the effectiveness of Network Enabled Operations in a Coastal Wide Area Surveillance situation, with algorithms provided by several universities. This INFORM Lab testbed allows experimenting with high-level distributed information fusion, dynamic resource management and configuration management, given multiple constraints on the resources and their communications networks. This paper describes the architecture of INFORM Lab, the essential concepts of goals and situation evidence, a selected set of algorithms for distributed information fusion and dynamic resource management, as well as auto-configurable information fusion architectures. The testbed provides general services which include a multilayer plug-and-play architecture, and a general multi-agent framework based on John Boyd's OODA loop. The testbed's performance is demonstrated on 2 types of scenarios/vignettes for 1) cooperative search-and-rescue efforts, and 2) a noncooperative smuggling scenario involving many target ships and various methods of deceit. For each mission, an appropriate subset of Canadian airborne and naval platforms are dispatched to collect situation evidence, which is fused, and then used to modify the platform trajectories for the most efficient collection of further situation evidence. These platforms are fusion nodes which obey a Command and Control node hierarchy.

Report from the MPP Working Group to the NASA Associate Administrator for Space Science and Applications

NASA Technical Reports Server (NTRS)

Fischer, James R.; Grosch, Chester; Mcanulty, Michael; Odonnell, John; Storey, Owen

1987-01-01

NASA's Office of Space Science and Applications (OSSA) gave a select group of scientists the opportunity to test and implement their computational algorithms on the Massively Parallel Processor (MPP) located at Goddard Space Flight Center, beginning in late 1985. One year later, the Working Group presented its report, which addressed the following: algorithms, programming languages, architecture, programming environments, the way theory relates, and performance measured. The findings point to a number of demonstrated computational techniques for which the MPP architecture is ideally suited. For example, besides executing much faster on the MPP than on conventional computers, systolic VLSI simulation (where distances are short), lattice simulation, neural network simulation, and image problems were found to be easier to program on the MPP's architecture than on a CYBER 205 or even a VAX. The report also makes technical recommendations covering all aspects of MPP use, and recommendations concerning the future of the MPP and machines based on similar architectures, expansion of the Working Group, and study of the role of future parallel processors for space station, EOS, and the Great Observatories era.

Proceedings of the Third International Workshop on Neural Networks and Fuzzy Logic, volume 2

NASA Technical Reports Server (NTRS)

Culbert, Christopher J. (Editor)

1993-01-01

Papers presented at the Neural Networks and Fuzzy Logic Workshop sponsored by the National Aeronautics and Space Administration and cosponsored by the University of Houston, Clear Lake, held 1-3 Jun. 1992 at the Lyndon B. Johnson Space Center in Houston, Texas are included. During the three days approximately 50 papers were presented. Technical topics addressed included adaptive systems; learning algorithms; network architectures; vision; robotics; neurobiological connections; speech recognition and synthesis; fuzzy set theory and application, control and dynamics processing; space applications; fuzzy logic and neural network computers; approximate reasoning; and multiobject decision making.

Joint multiple fully connected convolutional neural network with extreme learning machine for hepatocellular carcinoma nuclei grading.

PubMed

Li, Siqi; Jiang, Huiyan; Pang, Wenbo

2017-05-01

Accurate cell grading of cancerous tissue pathological image is of great importance in medical diagnosis and treatment. This paper proposes a joint multiple fully connected convolutional neural network with extreme learning machine (MFC-CNN-ELM) architecture for hepatocellular carcinoma (HCC) nuclei grading. First, in preprocessing stage, each grayscale image patch with the fixed size is obtained using center-proliferation segmentation (CPS) method and the corresponding labels are marked under the guidance of three pathologists. Next, a multiple fully connected convolutional neural network (MFC-CNN) is designed to extract the multi-form feature vectors of each input image automatically, which considers multi-scale contextual information of deep layer maps sufficiently. After that, a convolutional neural network extreme learning machine (CNN-ELM) model is proposed to grade HCC nuclei. Finally, a back propagation (BP) algorithm, which contains a new up-sample method, is utilized to train MFC-CNN-ELM architecture. The experiment comparison results demonstrate that our proposed MFC-CNN-ELM has superior performance compared with related works for HCC nuclei grading. Meanwhile, external validation using ICPR 2014 HEp-2 cell dataset shows the good generalization of our MFC-CNN-ELM architecture. Copyright © 2017 Elsevier Ltd. All rights reserved.

A Distributed Prognostic Health Management Architecture

NASA Technical Reports Server (NTRS)

Bhaskar, Saha; Saha, Sankalita; Goebel, Kai

2009-01-01

This paper introduces a generic distributed prognostic health management (PHM) architecture with specific application to the electrical power systems domain. Current state-of-the-art PHM systems are mostly centralized in nature, where all the processing is reliant on a single processor. This can lead to loss of functionality in case of a crash of the central processor or monitor. Furthermore, with increases in the volume of sensor data as well as the complexity of algorithms, traditional centralized systems become unsuitable for successful deployment, and efficient distributed architectures are required. A distributed architecture though, is not effective unless there is an algorithmic framework to take advantage of its unique abilities. The health management paradigm envisaged here incorporates a heterogeneous set of system components monitored by a varied suite of sensors and a particle filtering (PF) framework that has the power and the flexibility to adapt to the different diagnostic and prognostic needs. Both the diagnostic and prognostic tasks are formulated as a particle filtering problem in order to explicitly represent and manage uncertainties; however, typically the complexity of the prognostic routine is higher than the computational power of one computational element ( CE). Individual CEs run diagnostic routines until the system variable being monitored crosses beyond a nominal threshold, upon which it coordinates with other networked CEs to run the prognostic routine in a distributed fashion. Implementation results from a network of distributed embedded devices monitoring a prototypical aircraft electrical power system are presented, where the CEs are Sun Microsystems Small Programmable Object Technology (SPOT) devices.

A decentralized training algorithm for Echo State Networks in distributed big data applications.

PubMed

Scardapane, Simone; Wang, Dianhui; Panella, Massimo

2016-06-01

The current big data deluge requires innovative solutions for performing efficient inference on large, heterogeneous amounts of information. Apart from the known challenges deriving from high volume and velocity, real-world big data applications may impose additional technological constraints, including the need for a fully decentralized training architecture. While several alternatives exist for training feed-forward neural networks in such a distributed setting, less attention has been devoted to the case of decentralized training of recurrent neural networks (RNNs). In this paper, we propose such an algorithm for a class of RNNs known as Echo State Networks. The algorithm is based on the well-known Alternating Direction Method of Multipliers optimization procedure. It is formulated only in terms of local exchanges between neighboring agents, without reliance on a coordinating node. Additionally, it does not require the communication of training patterns, which is a crucial component in realistic big data implementations. Experimental results on large scale artificial datasets show that it compares favorably with a fully centralized implementation, in terms of speed, efficiency and generalization accuracy. Copyright © 2015 Elsevier Ltd. All rights reserved.

Energy efficient sensor network implementations

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

Frigo, Janette R; Raby, Eric Y; Brennan, Sean M

In this paper, we discuss a low power embedded sensor node architecture we are developing for distributed sensor network systems deployed in a natural environment. In particular, we examine the sensor node for energy efficient processing-at-the-sensor. We analyze the following modes of operation; event detection, sleep(wake-up), data acquisition, data processing modes using low power, high performance embedded technology such as specialized embedded DSP processors and a low power FPGAs at the sensing node. We use compute intensive sensor node applications: an acoustic vehicle classifier (frequency domain analysis) and a video license plate identification application (learning algorithm) as a case study.more » We report performance and total energy usage for our system implementations and discuss the system architecture design trade offs.« less

Deep 3D convolution neural network for CT brain hemorrhage classification

NASA Astrophysics Data System (ADS)

Jnawali, Kamal; Arbabshirani, Mohammad R.; Rao, Navalgund; Patel, Alpen A.

2018-02-01

Intracranial hemorrhage is a critical conditional with the high mortality rate that is typically diagnosed based on head computer tomography (CT) images. Deep learning algorithms, in particular, convolution neural networks (CNN), are becoming the methodology of choice in medical image analysis for a variety of applications such as computer-aided diagnosis, and segmentation. In this study, we propose a fully automated deep learning framework which learns to detect brain hemorrhage based on cross sectional CT images. The dataset for this work consists of 40,367 3D head CT studies (over 1.5 million 2D images) acquired retrospectively over a decade from multiple radiology facilities at Geisinger Health System. The proposed algorithm first extracts features using 3D CNN and then detects brain hemorrhage using the logistic function as the last layer of the network. Finally, we created an ensemble of three different 3D CNN architectures to improve the classification accuracy. The area under the curve (AUC) of the receiver operator characteristic (ROC) curve of the ensemble of three architectures was 0.87. Their results are very promising considering the fact that the head CT studies were not controlled for slice thickness, scanner type, study protocol or any other settings. Moreover, the proposed algorithm reliably detected various types of hemorrhage within the skull. This work is one of the first applications of 3D CNN trained on a large dataset of cross sectional medical images for detection of a critical radiological condition

Advanced algorithms for distributed fusion

NASA Astrophysics Data System (ADS)

Gelfand, A.; Smith, C.; Colony, M.; Bowman, C.; Pei, R.; Huynh, T.; Brown, C.

2008-03-01

The US Military has been undergoing a radical transition from a traditional "platform-centric" force to one capable of performing in a "Network-Centric" environment. This transformation will place all of the data needed to efficiently meet tactical and strategic goals at the warfighter's fingertips. With access to this information, the challenge of fusing data from across the batttlespace into an operational picture for real-time Situational Awareness emerges. In such an environment, centralized fusion approaches will have limited application due to the constraints of real-time communications networks and computational resources. To overcome these limitations, we are developing a formalized architecture for fusion and track adjudication that allows the distribution of fusion processes over a dynamically created and managed information network. This network will support the incorporation and utilization of low level tracking information within the Army Distributed Common Ground System (DCGS-A) or Future Combat System (FCS). The framework is based on Bowman's Dual Node Network (DNN) architecture that utilizes a distributed network of interlaced fusion and track adjudication nodes to build and maintain a globally consistent picture across all assets.

Analysis of Accuracy and Epoch on Back-propagation BFGS Quasi-Newton

NASA Astrophysics Data System (ADS)

Silaban, Herlan; Zarlis, Muhammad; Sawaluddin

2017-12-01

Back-propagation is one of the learning algorithms on artificial neural networks that have been widely used to solve various problems, such as pattern recognition, prediction and classification. The Back-propagation architecture will affect the outcome of learning processed. BFGS Quasi-Newton is one of the functions that can be used to change the weight of back-propagation. This research tested some back-propagation architectures using classical back-propagation and back-propagation with BFGS. There are 7 architectures that have been tested on glass dataset with various numbers of neurons, 6 architectures with 1 hidden layer and 1 architecture with 2 hidden layers. BP with BFGS improves the convergence of the learning process. The average improvement convergence is 98.34%. BP with BFGS is more optimal on architectures with smaller number of neurons with decreased epoch number is 94.37% with the increase of accuracy about 0.5%.

Visual question answering using hierarchical dynamic memory networks

NASA Astrophysics Data System (ADS)

Shang, Jiayu; Li, Shiren; Duan, Zhikui; Huang, Junwei

2018-04-01

Visual Question Answering (VQA) is one of the most popular research fields in machine learning which aims to let the computer learn to answer natural language questions with images. In this paper, we propose a new method called hierarchical dynamic memory networks (HDMN), which takes both question attention and visual attention into consideration impressed by Co-Attention method, which is the best (or among the best) algorithm for now. Additionally, we use bi-directional LSTMs, which have a better capability to remain more information from the question and image, to replace the old unit so that we can capture information from both past and future sentences to be used. Then we rebuild the hierarchical architecture for not only question attention but also visual attention. What's more, we accelerate the algorithm via a new technic called Batch Normalization which helps the network converge more quickly than other algorithms. The experimental result shows that our model improves the state of the art on the large COCO-QA dataset, compared with other methods.

"Catch the Pendulum": The Problem of Asymmetric Data Delivery in Electromagnetic Nanonetworks.

PubMed

Islam, Nabiul; Misra, Sudip

2016-09-01

The network of novel nano-material based nanodevices, known as nanoscale communication networks or nanonetworks has ushered a new communication paradigm in the terahertz band (0.1-10 THz). In this work, first we envisage an architecture of nanonetworks-based Coronary Heart Disease (CHD) monitoring, consisting of nano-macro interface (NM) and nanodevice-embedded Drug Eluting Stents (DESs), termed as nanoDESs. Next, we study the problem of asymmetric data delivery in such nanonetworks-based systems and propose a simple distance-aware power allocation algorithm, named catch-the-pendulum, which optimizes the energy consumption of nanoDESs for communicating data from the underlying nanonetworks to radio frequency (RF) based macro-scale communication networks. The algorithm exploits the periodic change in mean distance between a nanoDES, inserted inside the affected coronary artery, and the NM, fitted in the intercostal space of the rib cage of a patient suffering from a CHD. Extensive simulations confirm superior performance of the proposed algorithm with respect to energy consumption, packet delivery, and shutdown phase.

Research on key technologies for data-interoperability-based metadata, data compression and encryption, and their application

NASA Astrophysics Data System (ADS)

Yu, Xu; Shao, Quanqin; Zhu, Yunhai; Deng, Yuejin; Yang, Haijun

2006-10-01

With the development of informationization and the separation between data management departments and application departments, spatial data sharing becomes one of the most important objectives for the spatial information infrastructure construction, and spatial metadata management system, data transmission security and data compression are the key technologies to realize spatial data sharing. This paper discusses the key technologies for metadata based on data interoperability, deeply researches the data compression algorithms such as adaptive Huffman algorithm, LZ77 and LZ78 algorithm, studies to apply digital signature technique to encrypt spatial data, which can not only identify the transmitter of spatial data, but also find timely whether the spatial data are sophisticated during the course of network transmission, and based on the analysis of symmetric encryption algorithms including 3DES,AES and asymmetric encryption algorithm - RAS, combining with HASH algorithm, presents a improved mix encryption method for spatial data. Digital signature technology and digital watermarking technology are also discussed. Then, a new solution of spatial data network distribution is put forward, which adopts three-layer architecture. Based on the framework, we give a spatial data network distribution system, which is efficient and safe, and also prove the feasibility and validity of the proposed solution.

Rapid Human-Computer Interactive Conceptual Design of Mobile and Manipulative Robot Systems

DTIC Science & Technology

2015-05-19

algorithm based on Age-Fitness Pareto Optimization (AFPO) ([9]) with an additional user prefer- ence objective and a neural network-based user model, we...greater than 40, which is about 5 times further than any robot traveled in our experiments. 6 3.3 Methods The algorithm uses a client -server computational...architecture. The client here is an interactive pro- gram which takes a pair of controllers as input, simulates4 two copies of the robot with

Fast learning method for convolutional neural networks using extreme learning machine and its application to lane detection.

PubMed

Kim, Jihun; Kim, Jonghong; Jang, Gil-Jin; Lee, Minho

2017-03-01

Deep learning has received significant attention recently as a promising solution to many problems in the area of artificial intelligence. Among several deep learning architectures, convolutional neural networks (CNNs) demonstrate superior performance when compared to other machine learning methods in the applications of object detection and recognition. We use a CNN for image enhancement and the detection of driving lanes on motorways. In general, the process of lane detection consists of edge extraction and line detection. A CNN can be used to enhance the input images before lane detection by excluding noise and obstacles that are irrelevant to the edge detection result. However, training conventional CNNs requires considerable computation and a big dataset. Therefore, we suggest a new learning algorithm for CNNs using an extreme learning machine (ELM). The ELM is a fast learning method used to calculate network weights between output and hidden layers in a single iteration and thus, can dramatically reduce learning time while producing accurate results with minimal training data. A conventional ELM can be applied to networks with a single hidden layer; as such, we propose a stacked ELM architecture in the CNN framework. Further, we modify the backpropagation algorithm to find the targets of hidden layers and effectively learn network weights while maintaining performance. Experimental results confirm that the proposed method is effective in reducing learning time and improving performance. Copyright © 2016 Elsevier Ltd. All rights reserved.

APRON: A Cellular Processor Array Simulation and Hardware Design Tool

NASA Astrophysics Data System (ADS)

Barr, David R. W.; Dudek, Piotr

2009-12-01

We present a software environment for the efficient simulation of cellular processor arrays (CPAs). This software (APRON) is used to explore algorithms that are designed for massively parallel fine-grained processor arrays, topographic multilayer neural networks, vision chips with SIMD processor arrays, and related architectures. The software uses a highly optimised core combined with a flexible compiler to provide the user with tools for the design of new processor array hardware architectures and the emulation of existing devices. We present performance benchmarks for the software processor array implemented on standard commodity microprocessors. APRON can be configured to use additional processing hardware if necessary and can be used as a complete graphical user interface and development environment for new or existing CPA systems, allowing more users to develop algorithms for CPA systems.

Real-time support for high performance aircraft operation

NASA Technical Reports Server (NTRS)

Vidal, Jacques J.

1989-01-01

The feasibility of real-time processing schemes using artificial neural networks (ANNs) is investigated. A rationale for digital neural nets is presented and a general processor architecture for control applications is illustrated. Research results on ANN structures for real-time applications are given. Research results on ANN algorithms for real-time control are also shown.

Convolutional networks for fast, energy-efficient neuromorphic computing

PubMed Central

Esser, Steven K.; Merolla, Paul A.; Arthur, John V.; Cassidy, Andrew S.; Appuswamy, Rathinakumar; Andreopoulos, Alexander; Berg, David J.; McKinstry, Jeffrey L.; Melano, Timothy; Barch, Davis R.; di Nolfo, Carmelo; Datta, Pallab; Amir, Arnon; Taba, Brian; Flickner, Myron D.; Modha, Dharmendra S.

2016-01-01

Deep networks are now able to achieve human-level performance on a broad spectrum of recognition tasks. Independently, neuromorphic computing has now demonstrated unprecedented energy-efficiency through a new chip architecture based on spiking neurons, low precision synapses, and a scalable communication network. Here, we demonstrate that neuromorphic computing, despite its novel architectural primitives, can implement deep convolution networks that (i) approach state-of-the-art classification accuracy across eight standard datasets encompassing vision and speech, (ii) perform inference while preserving the hardware’s underlying energy-efficiency and high throughput, running on the aforementioned datasets at between 1,200 and 2,600 frames/s and using between 25 and 275 mW (effectively >6,000 frames/s per Watt), and (iii) can be specified and trained using backpropagation with the same ease-of-use as contemporary deep learning. This approach allows the algorithmic power of deep learning to be merged with the efficiency of neuromorphic processors, bringing the promise of embedded, intelligent, brain-inspired computing one step closer. PMID:27651489

Convolutional networks for fast, energy-efficient neuromorphic computing.

PubMed

Esser, Steven K; Merolla, Paul A; Arthur, John V; Cassidy, Andrew S; Appuswamy, Rathinakumar; Andreopoulos, Alexander; Berg, David J; McKinstry, Jeffrey L; Melano, Timothy; Barch, Davis R; di Nolfo, Carmelo; Datta, Pallab; Amir, Arnon; Taba, Brian; Flickner, Myron D; Modha, Dharmendra S

2016-10-11

Deep networks are now able to achieve human-level performance on a broad spectrum of recognition tasks. Independently, neuromorphic computing has now demonstrated unprecedented energy-efficiency through a new chip architecture based on spiking neurons, low precision synapses, and a scalable communication network. Here, we demonstrate that neuromorphic computing, despite its novel architectural primitives, can implement deep convolution networks that (i) approach state-of-the-art classification accuracy across eight standard datasets encompassing vision and speech, (ii) perform inference while preserving the hardware's underlying energy-efficiency and high throughput, running on the aforementioned datasets at between 1,200 and 2,600 frames/s and using between 25 and 275 mW (effectively >6,000 frames/s per Watt), and (iii) can be specified and trained using backpropagation with the same ease-of-use as contemporary deep learning. This approach allows the algorithmic power of deep learning to be merged with the efficiency of neuromorphic processors, bringing the promise of embedded, intelligent, brain-inspired computing one step closer.

QKD-Based Secured Burst Integrity Design for Optical Burst Switched Networks

NASA Astrophysics Data System (ADS)

Balamurugan, A. M.; Sivasubramanian, A.; Parvathavarthini, B.

2016-03-01

The field of optical transmission has undergone numerous advancements and is still being researched mainly due to the fact that optical data transmission can be done at enormous speeds. It is quite evident that people prefer optical communication when it comes to large amount of data involving its transmission. The concept of switching in networks has matured enormously with several researches, architecture to implement and methods starting with Optical circuit switching to Optical Burst Switching. Optical burst switching is regarded as viable solution for switching bursts over networks but has several security vulnerabilities. However, this work exploited the security issues associated with Optical Burst Switching with respect to integrity of burst. This proposed Quantum Key based Secure Hash Algorithm (QKBSHA-512) with enhanced compression function design provides better avalanche effect over the conventional integrity algorithms.

Automatic disease diagnosis using optimised weightless neural networks for low-power wearable devices

PubMed Central

Edla, Damodar Reddy; Kuppili, Venkatanareshbabu; Dharavath, Ramesh; Beechu, Nareshkumar Reddy

2017-01-01

Low-power wearable devices for disease diagnosis are used at anytime and anywhere. These are non-invasive and pain-free for the better quality of life. However, these devices are resource constrained in terms of memory and processing capability. Memory constraint allows these devices to store a limited number of patterns and processing constraint provides delayed response. It is a challenging task to design a robust classification system under above constraints with high accuracy. In this Letter, to resolve this problem, a novel architecture for weightless neural networks (WNNs) has been proposed. It uses variable sized random access memories to optimise the memory usage and a modified binary TRIE data structure for reducing the test time. In addition, a bio-inspired-based genetic algorithm has been employed to improve the accuracy. The proposed architecture is experimented on various disease datasets using its software and hardware realisations. The experimental results prove that the proposed architecture achieves better performance in terms of accuracy, memory saving and test time as compared to standard WNNs. It also outperforms in terms of accuracy as compared to conventional neural network-based classifiers. The proposed architecture is a powerful part of most of the low-power wearable devices for the solution of memory, accuracy and time issues. PMID:28868148

Sampling Approaches for Multi-Domain Internet Performance Measurement Infrastructures

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

Calyam, Prasad

2014-09-15

The next-generation of high-performance networks being developed in DOE communities are critical for supporting current and emerging data-intensive science applications. The goal of this project is to investigate multi-domain network status sampling techniques and tools to measure/analyze performance, and thereby provide “network awareness” to end-users and network operators in DOE communities. We leverage the infrastructure and datasets available through perfSONAR, which is a multi-domain measurement framework that has been widely deployed in high-performance computing and networking communities; the DOE community is a core developer and the largest adopter of perfSONAR. Our investigations include development of semantic scheduling algorithms, measurement federationmore » policies, and tools to sample multi-domain and multi-layer network status within perfSONAR deployments. We validate our algorithms and policies with end-to-end measurement analysis tools for various monitoring objectives such as network weather forecasting, anomaly detection, and fault-diagnosis. In addition, we develop a multi-domain architecture for an enterprise-specific perfSONAR deployment that can implement monitoring-objective based sampling and that adheres to any domain-specific measurement policies.« less

Complexity Optimization and High-Throughput Low-Latency Hardware Implementation of a Multi-Electrode Spike-Sorting Algorithm

PubMed Central

Dragas, Jelena; Jäckel, David; Hierlemann, Andreas; Franke, Felix

2017-01-01

Reliable real-time low-latency spike sorting with large data throughput is essential for studies of neural network dynamics and for brain-machine interfaces (BMIs), in which the stimulation of neural networks is based on the networks' most recent activity. However, the majority of existing multi-electrode spike-sorting algorithms are unsuited for processing high quantities of simultaneously recorded data. Recording from large neuronal networks using large high-density electrode sets (thousands of electrodes) imposes high demands on the data-processing hardware regarding computational complexity and data transmission bandwidth; this, in turn, entails demanding requirements in terms of chip area, memory resources and processing latency. This paper presents computational complexity optimization techniques, which facilitate the use of spike-sorting algorithms in large multi-electrode-based recording systems. The techniques are then applied to a previously published algorithm, on its own, unsuited for large electrode set recordings. Further, a real-time low-latency high-performance VLSI hardware architecture of the modified algorithm is presented, featuring a folded structure capable of processing the activity of hundreds of neurons simultaneously. The hardware is reconfigurable “on-the-fly” and adaptable to the nonstationarities of neuronal recordings. By transmitting exclusively spike time stamps and/or spike waveforms, its real-time processing offers the possibility of data bandwidth and data storage reduction. PMID:25415989

Complexity optimization and high-throughput low-latency hardware implementation of a multi-electrode spike-sorting algorithm.

PubMed

Dragas, Jelena; Jackel, David; Hierlemann, Andreas; Franke, Felix

2015-03-01

Reliable real-time low-latency spike sorting with large data throughput is essential for studies of neural network dynamics and for brain-machine interfaces (BMIs), in which the stimulation of neural networks is based on the networks' most recent activity. However, the majority of existing multi-electrode spike-sorting algorithms are unsuited for processing high quantities of simultaneously recorded data. Recording from large neuronal networks using large high-density electrode sets (thousands of electrodes) imposes high demands on the data-processing hardware regarding computational complexity and data transmission bandwidth; this, in turn, entails demanding requirements in terms of chip area, memory resources and processing latency. This paper presents computational complexity optimization techniques, which facilitate the use of spike-sorting algorithms in large multi-electrode-based recording systems. The techniques are then applied to a previously published algorithm, on its own, unsuited for large electrode set recordings. Further, a real-time low-latency high-performance VLSI hardware architecture of the modified algorithm is presented, featuring a folded structure capable of processing the activity of hundreds of neurons simultaneously. The hardware is reconfigurable “on-the-fly” and adaptable to the nonstationarities of neuronal recordings. By transmitting exclusively spike time stamps and/or spike waveforms, its real-time processing offers the possibility of data bandwidth and data storage reduction.

Neural architecture design based on extreme learning machine.

PubMed

Bueno-Crespo, Andrés; García-Laencina, Pedro J; Sancho-Gómez, José-Luis

2013-12-01

Selection of the optimal neural architecture to solve a pattern classification problem entails to choose the relevant input units, the number of hidden neurons and its corresponding interconnection weights. This problem has been widely studied in many research works but their solutions usually involve excessive computational cost in most of the problems and they do not provide a unique solution. This paper proposes a new technique to efficiently design the MultiLayer Perceptron (MLP) architecture for classification using the Extreme Learning Machine (ELM) algorithm. The proposed method provides a high generalization capability and a unique solution for the architecture design. Moreover, the selected final network only retains those input connections that are relevant for the classification task. Experimental results show these advantages. Copyright © 2013 Elsevier Ltd. All rights reserved.

On-line training of recurrent neural networks with continuous topology adaptation.

PubMed

Obradovic, D

1996-01-01

This paper presents an online procedure for training dynamic neural networks with input-output recurrences whose topology is continuously adjusted to the complexity of the target system dynamics. This is accomplished by changing the number of the elements of the network hidden layer whenever the existing topology cannot capture the dynamics presented by the new data. The training mechanism is based on the suitably altered extended Kalman filter (EKF) algorithm which is simultaneously used for the network parameter adjustment and for its state estimation. The network consists of a single hidden layer with Gaussian radial basis functions (GRBF), and a linear output layer. The choice of the GRBF is induced by the requirements of the online learning. The latter implies the network architecture which permits only local influence of the new data point in order not to forget the previously learned dynamics. The continuous topology adaptation is implemented in our algorithm to avoid memory and computational problems of using a regular grid of GRBF'S which covers the network input space. Furthermore, we show that the resulting parameter increase can be handled "smoothly" without interfering with the already acquired information. If the target system dynamics are changing over time, we show that a suitable forgetting factor can be used to "unlearn" the no longer-relevant dynamics. The quality of the recurrent network training algorithm is demonstrated on the identification of nonlinear dynamic systems.

Parallel Signal Processing and System Simulation using aCe

NASA Technical Reports Server (NTRS)

Dorband, John E.; Aburdene, Maurice F.

2003-01-01

Recently, networked and cluster computation have become very popular for both signal processing and system simulation. A new language is ideally suited for parallel signal processing applications and system simulation since it allows the programmer to explicitly express the computations that can be performed concurrently. In addition, the new C based parallel language (ace C) for architecture-adaptive programming allows programmers to implement algorithms and system simulation applications on parallel architectures by providing them with the assurance that future parallel architectures will be able to run their applications with a minimum of modification. In this paper, we will focus on some fundamental features of ace C and present a signal processing application (FFT).

Optical multicast system for data center networks.

PubMed

Samadi, Payman; Gupta, Varun; Xu, Junjie; Wang, Howard; Zussman, Gil; Bergman, Keren

2015-08-24

We present the design and experimental evaluation of an Optical Multicast System for Data Center Networks, a hardware-software system architecture that uniquely integrates passive optical splitters in a hybrid network architecture for faster and simpler delivery of multicast traffic flows. An application-driven control plane manages the integrated optical and electronic switched traffic routing in the data plane layer. The control plane includes a resource allocation algorithm to optimally assign optical splitters to the flows. The hardware architecture is built on a hybrid network with both Electronic Packet Switching (EPS) and Optical Circuit Switching (OCS) networks to aggregate Top-of-Rack switches. The OCS is also the connectivity substrate of splitters to the optical network. The optical multicast system implementation requires only commodity optical components. We built a prototype and developed a simulation environment to evaluate the performance of the system for bulk multicasting. Experimental and numerical results show simultaneous delivery of multicast flows to all receivers with steady throughput. Compared to IP multicast that is the electronic counterpart, optical multicast performs with less protocol complexity and reduced energy consumption. Compared to peer-to-peer multicast methods, it achieves at minimum an order of magnitude higher throughput for flows under 250 MB with significantly less connection overheads. Furthermore, for delivering 20 TB of data containing only 15% multicast flows, it reduces the total delivery energy consumption by 50% and improves latency by 55% compared to a data center with a sole non-blocking EPS network.

Local Estimators for Spacecraft Formation Flying

NASA Technical Reports Server (NTRS)

Fathpour, Nanaz; Hadaegh, Fred Y.; Mesbahi, Mehran; Nabi, Marzieh

2011-01-01

A formation estimation architecture for formation flying builds upon the local information exchange among multiple local estimators. Spacecraft formation flying involves the coordination of states among multiple spacecraft through relative sensing, inter-spacecraft communication, and control. Most existing formation flying estimation algorithms can only be supported via highly centralized, all-to-all, static relative sensing. New algorithms are needed that are scalable, modular, and robust to variations in the topology and link characteristics of the formation exchange network. These distributed algorithms should rely on a local information-exchange network, relaxing the assumptions on existing algorithms. In this research, it was shown that only local observability is required to design a formation estimator and control law. The approach relies on breaking up the overall information-exchange network into sequence of local subnetworks, and invoking an agreement-type filter to reach consensus among local estimators within each local network. State estimates were obtained by a set of local measurements that were passed through a set of communicating Kalman filters to reach an overall state estimation for the formation. An optimization approach was also presented by means of which diffused estimates over the network can be incorporated in the local estimates obtained by each estimator via local measurements. This approach compares favorably with that obtained by a centralized Kalman filter, which requires complete knowledge of the raw measurement available to each estimator.

Power Allocation and Outage Probability Analysis for SDN-based Radio Access Networks

NASA Astrophysics Data System (ADS)

Zhao, Yongxu; Chen, Yueyun; Mai, Zhiyuan

2018-01-01

In this paper, performance of Access network Architecture based SDN (Software Defined Network) is analyzed with respect to the power allocation issue. A power allocation scheme PSO-PA (Particle Swarm Optimization-power allocation) algorithm is proposed, the proposed scheme is subjected to constant total power with the objective of minimizing system outage probability. The entire access network resource configuration is controlled by the SDN controller, then it sends the optimized power distribution factor to the base station source node (SN) and the relay node (RN). Simulation results show that the proposed scheme reduces the system outage probability at a low complexity.

Proceedings of the Third International Workshop on Neural Networks and Fuzzy Logic, volume 1

NASA Technical Reports Server (NTRS)

Culbert, Christopher J. (Editor)

1993-01-01

Documented here are papers presented at the Neural Networks and Fuzzy Logic Workshop sponsored by the National Aeronautics and Space Administration and cosponsored by the University of Houston, Clear Lake. The workshop was held June 1-3, 1992 at the Lyndon B. Johnson Space Center in Houston, Texas. During the three days approximately 50 papers were presented. Technical topics addressed included adaptive systems; learning algorithms; network architectures; vision; robotics; neurobiological connections; speech recognition and synthesis; fuzzy set theory and application, control, and dynamics processing; space applications; fuzzy logic and neural network computers; approximate reasoning; and multiobject decision making.

Efficient traffic grooming with dynamic ONU grouping for multiple-OLT-based access network

NASA Astrophysics Data System (ADS)

Zhang, Shizong; Gu, Rentao; Ji, Yuefeng; Wang, Hongxiang

2015-12-01

Fast bandwidth growth urges large-scale high-density access scenarios, where the multiple Passive Optical Networking (PON) system clustered deployment can be adopted as an appropriate solution to fulfill the huge bandwidth demands, especially for a future 5G mobile network. However, the lack of interaction between different optical line terminals (OLTs) results in part of the bandwidth resources waste. To increase the bandwidth efficiency, as well as reduce bandwidth pressure at the edge of a network, we propose a centralized flexible PON architecture based on Time- and Wavelength-Division Multiplexing PON (TWDM PON). It can provide flexible affiliation for optical network units (ONUs) and different OLTs to support access network traffic localization. Specifically, a dynamic ONU grouping algorithm (DGA) is provided to obtain the minimal OLT outbound traffic. Simulation results show that DGA obtains an average 25.23% traffic gain increment under different OLT numbers within a small ONU number situation, and the traffic gain will increase dramatically with the increment of the ONU number. As the DGA can be deployed easily as an application running above the centralized control plane, the proposed architecture can be helpful to improve the network efficiency for future traffic-intensive access scenarios.

A feed-forward Hopfield neural network algorithm (FHNNA) with a colour satellite image for water quality mapping

NASA Astrophysics Data System (ADS)

Asal Kzar, Ahmed; Mat Jafri, M. Z.; Hwee San, Lim; Al-Zuky, Ali A.; Mutter, Kussay N.; Hassan Al-Saleh, Anwar

2016-06-01

There are many techniques that have been given for water quality problem, but the remote sensing techniques have proven their success, especially when the artificial neural networks are used as mathematical models with these techniques. Hopfield neural network is one type of artificial neural networks which is common, fast, simple, and efficient, but it when it deals with images that have more than two colours such as remote sensing images. This work has attempted to solve this problem via modifying the network that deals with colour remote sensing images for water quality mapping. A Feed-forward Hopfield Neural Network Algorithm (FHNNA) was modified and used with a satellite colour image from type of Thailand earth observation system (THEOS) for TSS mapping in the Penang strait, Malaysia, through the classification of TSS concentrations. The new algorithm is based essentially on three modifications: using HNN as feed-forward network, considering the weights of bitplanes, and non-self-architecture or zero diagonal of weight matrix, in addition, it depends on a validation data. The achieved map was colour-coded for visual interpretation. The efficiency of the new algorithm has found out by the higher correlation coefficient (R=0.979) and the lower root mean square error (RMSE=4.301) between the validation data that were divided into two groups. One used for the algorithm and the other used for validating the results. The comparison was with the minimum distance classifier. Therefore, TSS mapping of polluted water in Penang strait, Malaysia, can be performed using FHNNA with remote sensing technique (THEOS). It is a new and useful application of HNN, so it is a new model with remote sensing techniques for water quality mapping which is considered important environmental problem.

Adaptive architectures for resilient control of networked multiagent systems in the presence of misbehaving agents

NASA Astrophysics Data System (ADS)

Torre, Gerardo De La; Yucelen, Tansel

2018-03-01

Control algorithms of networked multiagent systems are generally computed distributively without having a centralised entity monitoring the activity of agents; and therefore, unforeseen adverse conditions such as uncertainties or attacks to the communication network and/or failure of agent-wise components can easily result in system instability and prohibit the accomplishment of system-level objectives. In this paper, we study resilient coordination of networked multiagent systems in the presence of misbehaving agents, i.e. agents that are subject to exogenous disturbances that represent a class of adverse conditions. In particular, a distributed adaptive control architecture is presented for directed and time-varying graph topologies to retrieve a desired networked multiagent system behaviour. Apart from the existing relevant literature that make specific assumptions on the graph topology and/or the fraction of misbehaving agents, we show that the considered class of adverse conditions can be mitigated by the proposed adaptive control approach that utilises a local state emulator - even if all agents are misbehaving. Illustrative numerical examples are provided to demonstrate the theoretical findings.

A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction.

PubMed

Kang, Eunhee; Min, Junhong; Ye, Jong Chul

2017-10-01

Due to the potential risk of inducing cancer, radiation exposure by X-ray CT devices should be reduced for routine patient scanning. However, in low-dose X-ray CT, severe artifacts typically occur due to photon starvation, beam hardening, and other causes, all of which decrease the reliability of the diagnosis. Thus, a high-quality reconstruction method from low-dose X-ray CT data has become a major research topic in the CT community. Conventional model-based de-noising approaches are, however, computationally very expensive, and image-domain de-noising approaches cannot readily remove CT-specific noise patterns. To tackle these problems, we want to develop a new low-dose X-ray CT algorithm based on a deep-learning approach. We propose an algorithm which uses a deep convolutional neural network (CNN) which is applied to the wavelet transform coefficients of low-dose CT images. More specifically, using a directional wavelet transform to extract the directional component of artifacts and exploit the intra- and inter- band correlations, our deep network can effectively suppress CT-specific noise. In addition, our CNN is designed with a residual learning architecture for faster network training and better performance. Experimental results confirm that the proposed algorithm effectively removes complex noise patterns from CT images derived from a reduced X-ray dose. In addition, we show that the wavelet-domain CNN is efficient when used to remove noise from low-dose CT compared to existing approaches. Our results were rigorously evaluated by several radiologists at the Mayo Clinic and won second place at the 2016 "Low-Dose CT Grand Challenge." To the best of our knowledge, this work is the first deep-learning architecture for low-dose CT reconstruction which has been rigorously evaluated and proven to be effective. In addition, the proposed algorithm, in contrast to existing model-based iterative reconstruction (MBIR) methods, has considerable potential to benefit from large data sets. Therefore, we believe that the proposed algorithm opens a new direction in the area of low-dose CT research. © 2017 American Association of Physicists in Medicine.

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.

Clustering of tethered satellite system simulation data by an adaptive neuro-fuzzy algorithm

NASA Technical Reports Server (NTRS)

Mitra, Sunanda; Pemmaraju, Surya

1992-01-01

Recent developments in neuro-fuzzy systems indicate that the concepts of adaptive pattern recognition, when used to identify appropriate control actions corresponding to clusters of patterns representing system states in dynamic nonlinear control systems, may result in innovative designs. A modular, unsupervised neural network architecture, in which fuzzy learning rules have been embedded is used for on-line identification of similar states. The architecture and control rules involved in Adaptive Fuzzy Leader Clustering (AFLC) allow this system to be incorporated in control systems for identification of system states corresponding to specific control actions. We have used this algorithm to cluster the simulation data of Tethered Satellite System (TSS) to estimate the range of delta voltages necessary to maintain the desired length rate of the tether. The AFLC algorithm is capable of on-line estimation of the appropriate control voltages from the corresponding length error and length rate error without a priori knowledge of their membership functions and familarity with the behavior of the Tethered Satellite System.

Artificial Neural Networks as an Architectural Design Tool-Generating New Detail Forms Based On the Roman Corinthian Order Capital

NASA Astrophysics Data System (ADS)

Radziszewski, Kacper

2017-10-01

The following paper presents the results of the research in the field of the machine learning, investigating the scope of application of the artificial neural networks algorithms as a tool in architectural design. The computational experiment was held using the backward propagation of errors method of training the artificial neural network, which was trained based on the geometry of the details of the Roman Corinthian order capital. During the experiment, as an input training data set, five local geometry parameters combined has given the best results: Theta, Pi, Rho in spherical coordinate system based on the capital volume centroid, followed by Z value of the Cartesian coordinate system and a distance from vertical planes created based on the capital symmetry. Additionally during the experiment, artificial neural network hidden layers optimal count and structure was found, giving results of the error below 0.2% for the mentioned before input parameters. Once successfully trained artificial network, was able to mimic the details composition on any other geometry type given. Despite of calculating the transformed geometry locally and separately for each of the thousands of surface points, system could create visually attractive and diverse, complex patterns. Designed tool, based on the supervised learning method of machine learning, gives possibility of generating new architectural forms- free of the designer’s imagination bounds. Implementing the infinitely broad computational methods of machine learning, or Artificial Intelligence in general, not only could accelerate and simplify the design process, but give an opportunity to explore never seen before, unpredictable forms or everyday architectural practice solutions.

An Information Theoretic Framework and Self-organizing Agent- based Sensor Network Architecture for Power Plant Condition Monitoring

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

Loparo, Kenneth; Kolacinski, Richard; Threeanaew, Wanchat

A central goal of the work was to enable both the extraction of all relevant information from sensor data, and the application of information gained from appropriate processing and fusion at the system level to operational control and decision-making at various levels of the control hierarchy through: 1. Exploiting the deep connection between information theory and the thermodynamic formalism, 2. Deployment using distributed intelligent agents with testing and validation in a hardware-in-the loop simulation environment. Enterprise architectures are the organizing logic for key business processes and IT infrastructure and, while the generality of current definitions provides sufficient flexibility, the currentmore » architecture frameworks do not inherently provide the appropriate structure. Of particular concern is that existing architecture frameworks often do not make a distinction between ``data'' and ``information.'' This work defines an enterprise architecture for health and condition monitoring of power plant equipment and further provides the appropriate foundation for addressing shortcomings in current architecture definition frameworks through the discovery of the information connectivity between the elements of a power generation plant. That is, to identify the correlative structure between available observations streams using informational measures. The principle focus here is on the implementation and testing of an emergent, agent-based, algorithm based on the foraging behavior of ants for eliciting this structure and on measures for characterizing differences between communication topologies. The elicitation algorithms are applied to data streams produced by a detailed numerical simulation of Alstom’s 1000 MW ultra-super-critical boiler and steam plant. The elicitation algorithm and topology characterization can be based on different informational metrics for detecting connectivity, e.g. mutual information and linear correlation.« less

Method and system for training dynamic nonlinear adaptive filters which have embedded memory

NASA Technical Reports Server (NTRS)

Rabinowitz, Matthew (Inventor)

2002-01-01

Described herein is a method and system for training nonlinear adaptive filters (or neural networks) which have embedded memory. Such memory can arise in a multi-layer finite impulse response (FIR) architecture, or an infinite impulse response (IIR) architecture. We focus on filter architectures with separate linear dynamic components and static nonlinear components. Such filters can be structured so as to restrict their degrees of computational freedom based on a priori knowledge about the dynamic operation to be emulated. The method is detailed for an FIR architecture which consists of linear FIR filters together with nonlinear generalized single layer subnets. For the IIR case, we extend the methodology to a general nonlinear architecture which uses feedback. For these dynamic architectures, we describe how one can apply optimization techniques which make updates closer to the Newton direction than those of a steepest descent method, such as backpropagation. We detail a novel adaptive modified Gauss-Newton optimization technique, which uses an adaptive learning rate to determine both the magnitude and direction of update steps. For a wide range of adaptive filtering applications, the new training algorithm converges faster and to a smaller value of cost than both steepest-descent methods such as backpropagation-through-time, and standard quasi-Newton methods. We apply the algorithm to modeling the inverse of a nonlinear dynamic tracking system 5, as well as a nonlinear amplifier 6.

Specialized Computer Systems for Environment Visualization

NASA Astrophysics Data System (ADS)

Al-Oraiqat, Anas M.; Bashkov, Evgeniy A.; Zori, Sergii A.

2018-06-01

The need for real time image generation of landscapes arises in various fields as part of tasks solved by virtual and augmented reality systems, as well as geographic information systems. Such systems provide opportunities for collecting, storing, analyzing and graphically visualizing geographic data. Algorithmic and hardware software tools for increasing the realism and efficiency of the environment visualization in 3D visualization systems are proposed. This paper discusses a modified path tracing algorithm with a two-level hierarchy of bounding volumes and finding intersections with Axis-Aligned Bounding Box. The proposed algorithm eliminates the branching and hence makes the algorithm more suitable to be implemented on the multi-threaded CPU and GPU. A modified ROAM algorithm is used to solve the qualitative visualization of reliefs' problems and landscapes. The algorithm is implemented on parallel systems—cluster and Compute Unified Device Architecture-networks. Results show that the implementation on MPI clusters is more efficient than Graphics Processing Unit/Graphics Processing Clusters and allows real-time synthesis. The organization and algorithms of the parallel GPU system for the 3D pseudo stereo image/video synthesis are proposed. With realizing possibility analysis on a parallel GPU-architecture of each stage, 3D pseudo stereo synthesis is performed. An experimental prototype of a specialized hardware-software system 3D pseudo stereo imaging and video was developed on the CPU/GPU. The experimental results show that the proposed adaptation of 3D pseudo stereo imaging to the architecture of GPU-systems is efficient. Also it accelerates the computational procedures of 3D pseudo-stereo synthesis for the anaglyph and anamorphic formats of the 3D stereo frame without performing optimization procedures. The acceleration is on average 11 and 54 times for test GPUs.

Study on Data Clustering and Intelligent Decision Algorithm of Indoor Localization

NASA Astrophysics Data System (ADS)

Liu, Zexi

2018-01-01

Indoor positioning technology enables the human beings to have the ability of positional perception in architectural space, and there is a shortage of single network coverage and the problem of location data redundancy. So this article puts forward the indoor positioning data clustering algorithm and intelligent decision-making research, design the basic ideas of multi-source indoor positioning technology, analyzes the fingerprint localization algorithm based on distance measurement, position and orientation of inertial device integration. By optimizing the clustering processing of massive indoor location data, the data normalization pretreatment, multi-dimensional controllable clustering center and multi-factor clustering are realized, and the redundancy of locating data is reduced. In addition, the path is proposed based on neural network inference and decision, design the sparse data input layer, the dynamic feedback hidden layer and output layer, low dimensional results improve the intelligent navigation path planning.

Calibration of neural networks using genetic algorithms, with application to optimal path planning

NASA Technical Reports Server (NTRS)

Smith, Terence R.; Pitney, Gilbert A.; Greenwood, Daniel

1987-01-01

Genetic algorithms (GA) are used to search the synaptic weight space of artificial neural systems (ANS) for weight vectors that optimize some network performance function. GAs do not suffer from some of the architectural constraints involved with other techniques and it is straightforward to incorporate terms into the performance function concerning the metastructure of the ANS. Hence GAs offer a remarkably general approach to calibrating ANS. GAs are applied to the problem of calibrating an ANS that finds optimal paths over a given surface. This problem involves training an ANS on a relatively small set of paths and then examining whether the calibrated ANS is able to find good paths between arbitrary start and end points on the surface.

Systems Engineering Design Via Experimental Operation Research: Complex Organizational Metric for Programmatic Risk Environments (COMPRE)

NASA Technical Reports Server (NTRS)

Mog, Robert A.

1999-01-01

Unique and innovative graph theory, neural network, organizational modeling, and genetic algorithms are applied to the design and evolution of programmatic and organizational architectures. Graph theory representations of programs and organizations increase modeling capabilities and flexibility, while illuminating preferable programmatic/organizational design features. Treating programs and organizations as neural networks results in better system synthesis, and more robust data modeling. Organizational modeling using covariance structures enhances the determination of organizational risk factors. Genetic algorithms improve programmatic evolution characteristics, while shedding light on rulebase requirements for achieving specified technological readiness levels, given budget and schedule resources. This program of research improves the robustness and verifiability of systems synthesis tools, including the Complex Organizational Metric for Programmatic Risk Environments (COMPRE).

A prior-based integrative framework for functional transcriptional regulatory network inference

PubMed Central

Siahpirani, Alireza F.

2017-01-01

Abstract Transcriptional regulatory networks specify regulatory proteins controlling the context-specific expression levels of genes. Inference of genome-wide regulatory networks is central to understanding gene regulation, but remains an open challenge. Expression-based network inference is among the most popular methods to infer regulatory networks, however, networks inferred from such methods have low overlap with experimentally derived (e.g. ChIP-chip and transcription factor (TF) knockouts) networks. Currently we have a limited understanding of this discrepancy. To address this gap, we first develop a regulatory network inference algorithm, based on probabilistic graphical models, to integrate expression with auxiliary datasets supporting a regulatory edge. Second, we comprehensively analyze our and other state-of-the-art methods on different expression perturbation datasets. Networks inferred by integrating sequence-specific motifs with expression have substantially greater agreement with experimentally derived networks, while remaining more predictive of expression than motif-based networks. Our analysis suggests natural genetic variation as the most informative perturbation for network inference, and, identifies core TFs whose targets are predictable from expression. Multiple reasons make the identification of targets of other TFs difficult, including network architecture and insufficient variation of TF mRNA level. Finally, we demonstrate the utility of our inference algorithm to infer stress-specific regulatory networks and for regulator prioritization. PMID:27794550

Online Adaboost-Based Parameterized Methods for Dynamic Distributed Network Intrusion Detection.

PubMed

Hu, Weiming; Gao, Jun; Wang, Yanguo; Wu, Ou; Maybank, Stephen

2014-01-01

Current network intrusion detection systems lack adaptability to the frequently changing network environments. Furthermore, intrusion detection in the new distributed architectures is now a major requirement. In this paper, we propose two online Adaboost-based intrusion detection algorithms. In the first algorithm, a traditional online Adaboost process is used where decision stumps are used as weak classifiers. In the second algorithm, an improved online Adaboost process is proposed, and online Gaussian mixture models (GMMs) are used as weak classifiers. We further propose a distributed intrusion detection framework, in which a local parameterized detection model is constructed in each node using the online Adaboost algorithm. A global detection model is constructed in each node by combining the local parametric models using a small number of samples in the node. This combination is achieved using an algorithm based on particle swarm optimization (PSO) and support vector machines. The global model in each node is used to detect intrusions. Experimental results show that the improved online Adaboost process with GMMs obtains a higher detection rate and a lower false alarm rate than the traditional online Adaboost process that uses decision stumps. Both the algorithms outperform existing intrusion detection algorithms. It is also shown that our PSO, and SVM-based algorithm effectively combines the local detection models into the global model in each node; the global model in a node can handle the intrusion types that are found in other nodes, without sharing the samples of these intrusion types.

A Survey on Node Clustering in Cognitive Radio Wireless Sensor Networks.

PubMed

Joshi, Gyanendra Prasad; Kim, Sung Won

2016-09-10

Cognitive radio wireless sensor networks (CR-WSNs) have attracted a great deal of attention recently due to the emerging spectrum scarcity issue. This work attempts to provide a detailed analysis of the role of node clustering in CR-WSNs. We outline the objectives, requirements, and advantages of node clustering in CR-WSNs. We describe how a CR-WSN with node clustering differs from conventional wireless sensor networks, and we discuss its characteristics, architecture, and topologies. We survey the existing clustering algorithms and compare their objectives and features. We suggest how clustering issues and challenges can be handled.

An Efficient Hardware Circuit for Spike Sorting Based on Competitive Learning Networks.

PubMed

Chen, Huan-Yuan; Chen, Chih-Chang; Hwang, Wen-Jyi

2017-09-28

This study aims to present an effective VLSI circuit for multi-channel spike sorting. The circuit supports the spike detection, feature extraction and classification operations. The detection circuit is implemented in accordance with the nonlinear energy operator algorithm. Both the peak detection and area computation operations are adopted for the realization of the hardware architecture for feature extraction. The resulting feature vectors are classified by a circuit for competitive learning (CL) neural networks. The CL circuit supports both online training and classification. In the proposed architecture, all the channels share the same detection, feature extraction, learning and classification circuits for a low area cost hardware implementation. The clock-gating technique is also employed for reducing the power dissipation. To evaluate the performance of the architecture, an application-specific integrated circuit (ASIC) implementation is presented. Experimental results demonstrate that the proposed circuit exhibits the advantages of a low chip area, a low power dissipation and a high classification success rate for spike sorting.

An Efficient Hardware Circuit for Spike Sorting Based on Competitive Learning Networks

PubMed Central

Chen, Huan-Yuan; Chen, Chih-Chang

2017-01-01

This study aims to present an effective VLSI circuit for multi-channel spike sorting. The circuit supports the spike detection, feature extraction and classification operations. The detection circuit is implemented in accordance with the nonlinear energy operator algorithm. Both the peak detection and area computation operations are adopted for the realization of the hardware architecture for feature extraction. The resulting feature vectors are classified by a circuit for competitive learning (CL) neural networks. The CL circuit supports both online training and classification. In the proposed architecture, all the channels share the same detection, feature extraction, learning and classification circuits for a low area cost hardware implementation. The clock-gating technique is also employed for reducing the power dissipation. To evaluate the performance of the architecture, an application-specific integrated circuit (ASIC) implementation is presented. Experimental results demonstrate that the proposed circuit exhibits the advantages of a low chip area, a low power dissipation and a high classification success rate for spike sorting. PMID:28956859

Algorithms and Libraries

NASA Technical Reports Server (NTRS)

Dongarra, Jack

1998-01-01

This exploratory study initiated our inquiry into algorithms and applications that would benefit by latency tolerant approach to algorithm building, including the construction of new algorithms where appropriate. In a multithreaded execution, when a processor reaches a point where remote memory access is necessary, the request is sent out on the network and a context--switch occurs to a new thread of computation. This effectively masks a long and unpredictable latency due to remote loads, thereby providing tolerance to remote access latency. We began to develop standards to profile various algorithm and application parameters, such as the degree of parallelism, granularity, precision, instruction set mix, interprocessor communication, latency etc. These tools will continue to develop and evolve as the Information Power Grid environment matures. To provide a richer context for this research, the project also focused on issues of fault-tolerance and computation migration of numerical algorithms and software. During the initial phase we tried to increase our understanding of the bottlenecks in single processor performance. Our work began by developing an approach for the automatic generation and optimization of numerical software for processors with deep memory hierarchies and pipelined functional units. Based on the results we achieved in this study we are planning to study other architectures of interest, including development of cost models, and developing code generators appropriate to these architectures.

Hybrid Architectures and Their Impact on Intelligent Design

NASA Technical Reports Server (NTRS)

Kandel, Abe

1996-01-01

In this presentation we investigate a novel framework for the design of autonomous fuzzy intelligent systems. The system integrates the following modules into a single autonomous entity: (1) a fuzzy expert system; (2) artificial neural network; (3) genetic algorithm; and (4) case-base reasoning. We describe the integration of these units into one intelligent structure and discuss potential applications.

ProperCAD: A portable object-oriented parallel environment for VLSI CAD

NASA Technical Reports Server (NTRS)

Ramkumar, Balkrishna; Banerjee, Prithviraj

1993-01-01

Most parallel algorithms for VLSI CAD proposed to date have one important drawback: they work efficiently only on machines that they were designed for. As a result, algorithms designed to date are dependent on the architecture for which they are developed and do not port easily to other parallel architectures. A new project under way to address this problem is described. A Portable object-oriented parallel environment for CAD algorithms (ProperCAD) is being developed. The objectives of this research are (1) to develop new parallel algorithms that run in a portable object-oriented environment (CAD algorithms using a general purpose platform for portable parallel programming called CARM is being developed and a C++ environment that is truly object-oriented and specialized for CAD applications is also being developed); and (2) to design the parallel algorithms around a good sequential algorithm with a well-defined parallel-sequential interface (permitting the parallel algorithm to benefit from future developments in sequential algorithms). One CAD application that has been implemented as part of the ProperCAD project, flat VLSI circuit extraction, is described. The algorithm, its implementation, and its performance on a range of parallel machines are discussed in detail. It currently runs on an Encore Multimax, a Sequent Symmetry, Intel iPSC/2 and i860 hypercubes, a NCUBE 2 hypercube, and a network of Sun Sparc workstations. Performance data for other applications that were developed are provided: namely test pattern generation for sequential circuits, parallel logic synthesis, and standard cell placement.

Securing Mobile Networks in an Operational Setting

NASA Technical Reports Server (NTRS)

Ivancic, William D.; Stewart, David H.; Bell, Terry L.; Paulsen, Phillip E.; Shell, Dan

2004-01-01

This paper describes a network demonstration and three month field trial of mobile networking using mobile-IPv4. The network was implemented as part of the US Coast Guard operational network which is a ".mil" network and requires stringent levels of security. The initial demonstrations took place in November 2002 and a three month field trial took place from July through September of 2003. The mobile network utilized encryptors capable of NSA-approved Type 1 algorithms, mobile router from Cisco Systems and 802.11 and satellite wireless links. This paper also describes a conceptual architecture for wide-scale deployment of secure mobile networking in operational environments where both private and public infrastructure is used. Additional issues presented include link costs, placement of encryptors and running routing protocols over layer-3 encryption devices.

Delivery of video-on-demand services using local storages within passive optical networks.

PubMed

Abeywickrama, Sandu; Wong, Elaine

2013-01-28

At present, distributed storage systems have been widely studied to alleviate Internet traffic build-up caused by high-bandwidth, on-demand applications. Distributed storage arrays located locally within the passive optical network were previously proposed to deliver Video-on-Demand services. As an added feature, a popularity-aware caching algorithm was also proposed to dynamically maintain the most popular videos in the storage arrays of such local storages. In this paper, we present a new dynamic bandwidth allocation algorithm to improve Video-on-Demand services over passive optical networks using local storages. The algorithm exploits the use of standard control packets to reduce the time taken for the initial request communication between the customer and the central office, and to maintain the set of popular movies in the local storage. We conduct packet level simulations to perform a comparative analysis of the Quality-of-Service attributes between two passive optical networks, namely the conventional passive optical network and one that is equipped with a local storage. Results from our analysis highlight that strategic placement of a local storage inside the network enables the services to be delivered with improved Quality-of-Service to the customer. We further formulate power consumption models of both architectures to examine the trade-off between enhanced Quality-of-Service performance versus the increased power requirement from implementing a local storage within the network.

Towards deep learning with segregated dendrites

PubMed Central

Guerguiev, Jordan; Lillicrap, Timothy P

2017-01-01

Deep learning has led to significant advances in artificial intelligence, in part, by adopting strategies motivated by neurophysiology. However, it is unclear whether deep learning could occur in the real brain. Here, we show that a deep learning algorithm that utilizes multi-compartment neurons might help us to understand how the neocortex optimizes cost functions. Like neocortical pyramidal neurons, neurons in our model receive sensory information and higher-order feedback in electrotonically segregated compartments. Thanks to this segregation, neurons in different layers of the network can coordinate synaptic weight updates. As a result, the network learns to categorize images better than a single layer network. Furthermore, we show that our algorithm takes advantage of multilayer architectures to identify useful higher-order representations—the hallmark of deep learning. This work demonstrates that deep learning can be achieved using segregated dendritic compartments, which may help to explain the morphology of neocortical pyramidal neurons. PMID:29205151

Towards deep learning with segregated dendrites.

PubMed

Guerguiev, Jordan; Lillicrap, Timothy P; Richards, Blake A

2017-12-05

Deep learning has led to significant advances in artificial intelligence, in part, by adopting strategies motivated by neurophysiology. However, it is unclear whether deep learning could occur in the real brain. Here, we show that a deep learning algorithm that utilizes multi-compartment neurons might help us to understand how the neocortex optimizes cost functions. Like neocortical pyramidal neurons, neurons in our model receive sensory information and higher-order feedback in electrotonically segregated compartments. Thanks to this segregation, neurons in different layers of the network can coordinate synaptic weight updates. As a result, the network learns to categorize images better than a single layer network. Furthermore, we show that our algorithm takes advantage of multilayer architectures to identify useful higher-order representations-the hallmark of deep learning. This work demonstrates that deep learning can be achieved using segregated dendritic compartments, which may help to explain the morphology of neocortical pyramidal neurons.

SURGNET: An Integrated Surgical Data Transmission System for Telesurgery.

PubMed

Natarajan, Sriram; Ganz, Aura

2009-01-01

Remote surgery information requires quick and reliable transmission between the surgeon and the patient site. However, the networks that interconnect the surgeon and patient sites are usually time varying and lossy which can cause packet loss and delay jitter. In this paper we propose SURGNET, a telesurgery system for which we developed the architecture, algorithms and implemented it on a testbed. The algorithms include adaptive packet prediction and buffer time adjustment techniques which reduce the negative effects caused by the lossy and time varying networks. To evaluate the proposed SURGNET system, at the therapist site, we implemented a therapist panel which controls the force feedback device movements and provides image analysis functionality. At the patient site we controlled a virtual reality applet built in Matlab. The varying network conditions were emulated using NISTNet emulator. Our results show that even for severe packet loss and variable delay jitter, the proposed integrated synchronization techniques significantly improve SURGNET performance.

Enhanced Higgs boson to τ(+)τ(-) search with deep learning.

PubMed

Baldi, P; Sadowski, P; Whiteson, D

2015-03-20

The Higgs boson is thought to provide the interaction that imparts mass to the fundamental fermions, but while measurements at the Large Hadron Collider (LHC) are consistent with this hypothesis, current analysis techniques lack the statistical power to cross the traditional 5σ significance barrier without more data. Deep learning techniques have the potential to increase the statistical power of this analysis by automatically learning complex, high-level data representations. In this work, deep neural networks are used to detect the decay of the Higgs boson to a pair of tau leptons. A Bayesian optimization algorithm is used to tune the network architecture and training algorithm hyperparameters, resulting in a deep network of eight nonlinear processing layers that improves upon the performance of shallow classifiers even without the use of features specifically engineered by physicists for this application. The improvement in discovery significance is equivalent to an increase in the accumulated data set of 25%.

A modular architecture for transparent computation in recurrent neural networks.

PubMed

Carmantini, Giovanni S; Beim Graben, Peter; Desroches, Mathieu; Rodrigues, Serafim

2017-01-01

Computation is classically studied in terms of automata, formal languages and algorithms; yet, the relation between neural dynamics and symbolic representations and operations is still unclear in traditional eliminative connectionism. Therefore, we suggest a unique perspective on this central issue, to which we would like to refer as transparent connectionism, by proposing accounts of how symbolic computation can be implemented in neural substrates. In this study we first introduce a new model of dynamics on a symbolic space, the versatile shift, showing that it supports the real-time simulation of a range of automata. We then show that the Gödelization of versatile shifts defines nonlinear dynamical automata, dynamical systems evolving on a vectorial space. Finally, we present a mapping between nonlinear dynamical automata and recurrent artificial neural networks. The mapping defines an architecture characterized by its granular modularity, where data, symbolic operations and their control are not only distinguishable in activation space, but also spatially localizable in the network itself, while maintaining a distributed encoding of symbolic representations. The resulting networks simulate automata in real-time and are programmed directly, in the absence of network training. To discuss the unique characteristics of the architecture and their consequences, we present two examples: (i) the design of a Central Pattern Generator from a finite-state locomotive controller, and (ii) the creation of a network simulating a system of interactive automata that supports the parsing of garden-path sentences as investigated in psycholinguistics experiments. Copyright © 2016 Elsevier Ltd. All rights reserved.

ARACNe-based inference, using curated microarray data, of Arabidopsis thaliana root transcriptional regulatory networks

PubMed Central

2014-01-01

Background Uncovering the complex transcriptional regulatory networks (TRNs) that underlie plant and animal development remains a challenge. However, a vast amount of data from public microarray experiments is available, which can be subject to inference algorithms in order to recover reliable TRN architectures. Results In this study we present a simple bioinformatics methodology that uses public, carefully curated microarray data and the mutual information algorithm ARACNe in order to obtain a database of transcriptional interactions. We used data from Arabidopsis thaliana root samples to show that the transcriptional regulatory networks derived from this database successfully recover previously identified root transcriptional modules and to propose new transcription factors for the SHORT ROOT/SCARECROW and PLETHORA pathways. We further show that these networks are a powerful tool to integrate and analyze high-throughput expression data, as exemplified by our analysis of a SHORT ROOT induction time-course microarray dataset, and are a reliable source for the prediction of novel root gene functions. In particular, we used our database to predict novel genes involved in root secondary cell-wall synthesis and identified the MADS-box TF XAL1/AGL12 as an unexpected participant in this process. Conclusions This study demonstrates that network inference using carefully curated microarray data yields reliable TRN architectures. In contrast to previous efforts to obtain root TRNs, that have focused on particular functional modules or tissues, our root transcriptional interactions provide an overview of the transcriptional pathways present in Arabidopsis thaliana roots and will likely yield a plethora of novel hypotheses to be tested experimentally. PMID:24739361

A fast new algorithm for a robot neurocontroller using inverse QR decomposition

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

Morris, A.S.; Khemaissia, S.

2000-01-01

A new adaptive neural network controller for robots is presented. The controller is based on direct adaptive techniques. Unlike many neural network controllers in the literature, inverse dynamical model evaluation is not required. A numerically robust, computationally efficient processing scheme for neutral network weight estimation is described, namely, the inverse QR decomposition (INVQR). The inverse QR decomposition and a weighted recursive least-squares (WRLS) method for neural network weight estimation is derived using Cholesky factorization of the data matrix. The algorithm that performs the efficient INVQR of the underlying space-time data matrix may be implemented in parallel on a triangular array.more » Furthermore, its systolic architecture is well suited for VLSI implementation. Another important benefit is well suited for VLSI implementation. Another important benefit of the INVQR decomposition is that it solves directly for the time-recursive least-squares filter vector, while avoiding the sequential back-substitution step required by the QR decomposition approaches.« less

The development of an artificial organic networks toolkit for LabVIEW.

PubMed

Ponce, Hiram; Ponce, Pedro; Molina, Arturo

2015-03-15

Two of the most challenging problems that scientists and researchers face when they want to experiment with new cutting-edge algorithms are the time-consuming for encoding and the difficulties for linking them with other technologies and devices. In that sense, this article introduces the artificial organic networks toolkit for LabVIEW™ (AON-TL) from the implementation point of view. The toolkit is based on the framework provided by the artificial organic networks technique, giving it the potential to add new algorithms in the future based on this technique. Moreover, the toolkit inherits both the rapid prototyping and the easy-to-use characteristics of the LabVIEW™ software (e.g., graphical programming, transparent usage of other softwares and devices, built-in programming event-driven for user interfaces), to make it simple for the end-user. In fact, the article describes the global architecture of the toolkit, with particular emphasis in the software implementation of the so-called artificial hydrocarbon networks algorithm. Lastly, the article includes two case studies for engineering purposes (i.e., sensor characterization) and chemistry applications (i.e., blood-brain barrier partitioning data model) to show the usage of the toolkit and the potential scalability of the artificial organic networks technique. © 2015 Wiley Periodicals, Inc.

An efficient and portable SIMD algorithm for charge/current deposition in Particle-In-Cell codes

DOE PAGES

Vincenti, H.; Lobet, M.; Lehe, R.; ...

2016-09-19

In current computer architectures, data movement (from die to network) is by far the most energy consuming part of an algorithm (≈20pJ/word on-die to ≈10,000 pJ/word on the network). To increase memory locality at the hardware level and reduce energy consumption related to data movement, future exascale computers tend to use many-core processors on each compute nodes that will have a reduced clock speed to allow for efficient cooling. To compensate for frequency decrease, machine vendors are making use of long SIMD instruction registers that are able to process multiple data with one arithmetic operator in one clock cycle. SIMD registermore » length is expected to double every four years. As a consequence, Particle-In-Cell (PIC) codes will have to achieve good vectorization to fully take advantage of these upcoming architectures. In this paper, we present a new algorithm that allows for efficient and portable SIMD vectorization of current/charge deposition routines that are, along with the field gathering routines, among the most time consuming parts of the PIC algorithm. Our new algorithm uses a particular data structure that takes into account memory alignment constraints and avoids gather/scat;ter instructions that can significantly affect vectorization performances on current CPUs. The new algorithm was successfully implemented in the 3D skeleton PIC code PICSAR and tested on Haswell Xeon processors (AVX2-256 bits wide data registers). Results show a factor of ×2 to ×2.5 speed-up in double precision for particle shape factor of orders 1–3. The new algorithm can be applied as is on future KNL (Knights Landing) architectures that will include AVX-512 instruction sets with 512 bits register lengths (8 doubles/16 singles). Program summary Program Title: vec_deposition Program Files doi:http://dx.doi.org/10.17632/nh77fv9k8c.1 Licensing provisions: BSD 3-Clause Programming language: Fortran 90 External routines/libraries:  OpenMP > 4.0 Nature of problem: Exascale architectures will have many-core processors per node with long vector data registers capable of performing one single instruction on multiple data during one clock cycle. Data register lengths are expected to double every four years and this pushes for new portable solutions for efficiently vectorizing Particle-In-Cell codes on these future many-core architectures. One of the main hotspot routines of the PIC algorithm is the current/charge deposition for which there is no efficient and portable vector algorithm. Solution method: Here we provide an efficient and portable vector algorithm of current/charge deposition routines that uses a new data structure, which significantly reduces gather/scatter operations. Vectorization is controlled using OpenMP 4.0 compiler directives for vectorization which ensures portability across different architectures. Restrictions: Here we do not provide the full PIC algorithm with an executable but only vector routines for current/charge deposition. These scalar/vector routines can be used as library routines in your 3D Particle-In-Cell code. However, to get the best performances out of vector routines you have to satisfy the two following requirements: (1) Your code should implement particle tiling (as explained in the manuscript) to allow for maximized cache reuse and reduce memory accesses that can hinder vector performances. The routines can be used directly on each particle tile. (2) You should compile your code with a Fortran 90 compiler (e.g Intel, gnu or cray) and provide proper alignment flags and compiler alignment directives (more details in README file).« less

An efficient and portable SIMD algorithm for charge/current deposition in Particle-In-Cell codes

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

Vincenti, H.; Lobet, M.; Lehe, R.

In current computer architectures, data movement (from die to network) is by far the most energy consuming part of an algorithm (≈20pJ/word on-die to ≈10,000 pJ/word on the network). To increase memory locality at the hardware level and reduce energy consumption related to data movement, future exascale computers tend to use many-core processors on each compute nodes that will have a reduced clock speed to allow for efficient cooling. To compensate for frequency decrease, machine vendors are making use of long SIMD instruction registers that are able to process multiple data with one arithmetic operator in one clock cycle. SIMD registermore » length is expected to double every four years. As a consequence, Particle-In-Cell (PIC) codes will have to achieve good vectorization to fully take advantage of these upcoming architectures. In this paper, we present a new algorithm that allows for efficient and portable SIMD vectorization of current/charge deposition routines that are, along with the field gathering routines, among the most time consuming parts of the PIC algorithm. Our new algorithm uses a particular data structure that takes into account memory alignment constraints and avoids gather/scat;ter instructions that can significantly affect vectorization performances on current CPUs. The new algorithm was successfully implemented in the 3D skeleton PIC code PICSAR and tested on Haswell Xeon processors (AVX2-256 bits wide data registers). Results show a factor of ×2 to ×2.5 speed-up in double precision for particle shape factor of orders 1–3. The new algorithm can be applied as is on future KNL (Knights Landing) architectures that will include AVX-512 instruction sets with 512 bits register lengths (8 doubles/16 singles). Program summary Program Title: vec_deposition Program Files doi:http://dx.doi.org/10.17632/nh77fv9k8c.1 Licensing provisions: BSD 3-Clause Programming language: Fortran 90 External routines/libraries:  OpenMP > 4.0 Nature of problem: Exascale architectures will have many-core processors per node with long vector data registers capable of performing one single instruction on multiple data during one clock cycle. Data register lengths are expected to double every four years and this pushes for new portable solutions for efficiently vectorizing Particle-In-Cell codes on these future many-core architectures. One of the main hotspot routines of the PIC algorithm is the current/charge deposition for which there is no efficient and portable vector algorithm. Solution method: Here we provide an efficient and portable vector algorithm of current/charge deposition routines that uses a new data structure, which significantly reduces gather/scatter operations. Vectorization is controlled using OpenMP 4.0 compiler directives for vectorization which ensures portability across different architectures. Restrictions: Here we do not provide the full PIC algorithm with an executable but only vector routines for current/charge deposition. These scalar/vector routines can be used as library routines in your 3D Particle-In-Cell code. However, to get the best performances out of vector routines you have to satisfy the two following requirements: (1) Your code should implement particle tiling (as explained in the manuscript) to allow for maximized cache reuse and reduce memory accesses that can hinder vector performances. The routines can be used directly on each particle tile. (2) You should compile your code with a Fortran 90 compiler (e.g Intel, gnu or cray) and provide proper alignment flags and compiler alignment directives (more details in README file).« less

Parallel asynchronous systems and image processing algorithms

NASA Technical Reports Server (NTRS)

Coon, D. D.; Perera, A. G. U.

1989-01-01

A new hardware approach to implementation of image processing algorithms is described. The approach is based on silicon devices which would permit an independent analog processing channel to be dedicated to evey pixel. A laminar architecture consisting of a stack of planar arrays of the device would form a two-dimensional array processor with a 2-D array of inputs located directly behind a focal plane detector array. A 2-D image data stream would propagate in neuronlike asynchronous pulse coded form through the laminar processor. Such systems would integrate image acquisition and image processing. Acquisition and processing would be performed concurrently as in natural vision systems. The research is aimed at implementation of algorithms, such as the intensity dependent summation algorithm and pyramid processing structures, which are motivated by the operation of natural vision systems. Implementation of natural vision algorithms would benefit from the use of neuronlike information coding and the laminar, 2-D parallel, vision system type architecture. Besides providing a neural network framework for implementation of natural vision algorithms, a 2-D parallel approach could eliminate the serial bottleneck of conventional processing systems. Conversion to serial format would occur only after raw intensity data has been substantially processed. An interesting challenge arises from the fact that the mathematical formulation of natural vision algorithms does not specify the means of implementation, so that hardware implementation poses intriguing questions involving vision science.

Efficient Construction of Mesostate Networks from Molecular Dynamics Trajectories.

PubMed

Vitalis, Andreas; Caflisch, Amedeo

2012-03-13

The coarse-graining of data from molecular simulations yields conformational space networks that may be used for predicting the system's long time scale behavior, to discover structural pathways connecting free energy basins in the system, or simply to represent accessible phase space regions of interest and their connectivities in a two-dimensional plot. In this contribution, we present a tree-based algorithm to partition conformations of biomolecules into sets of similar microstates, i.e., to coarse-grain trajectory data into mesostates. On account of utilizing an architecture similar to that of established tree-based algorithms, the proposed scheme operates in near-linear time with data set size. We derive expressions needed for the fast evaluation of mesostate properties and distances when employing typical choices for measures of similarity between microstates. Using both a pedagogically useful and a real-word application, the algorithm is shown to be robust with respect to tree height, which in addition to mesostate threshold size is the main adjustable parameter. It is demonstrated that the derived mesostate networks can preserve information regarding the free energy basins and barriers by which the system is characterized.

Characterization of robotics parallel algorithms and mapping onto a reconfigurable SIMD machine

NASA Technical Reports Server (NTRS)

Lee, C. S. G.; Lin, C. T.

1989-01-01

The kinematics, dynamics, Jacobian, and their corresponding inverse computations are six essential problems in the control of robot manipulators. Efficient parallel algorithms for these computations are discussed and analyzed. Their characteristics are identified and a scheme on the mapping of these algorithms to a reconfigurable parallel architecture is presented. Based on the characteristics including type of parallelism, degree of parallelism, uniformity of the operations, fundamental operations, data dependencies, and communication requirement, it is shown that most of the algorithms for robotic computations possess highly regular properties and some common structures, especially the linear recursive structure. Moreover, they are well-suited to be implemented on a single-instruction-stream multiple-data-stream (SIMD) computer with reconfigurable interconnection network. The model of a reconfigurable dual network SIMD machine with internal direct feedback is introduced. A systematic procedure internal direct feedback is introduced. A systematic procedure to map these computations to the proposed machine is presented. A new scheduling problem for SIMD machines is investigated and a heuristic algorithm, called neighborhood scheduling, that reorders the processing sequence of subtasks to reduce the communication time is described. Mapping results of a benchmark algorithm are illustrated and discussed.

Data Compression for Maskless Lithography Systems: Architecture, Algorithms and Implementation

DTIC Science & Technology

2008-05-19

Data Compression for Maskless Lithography Systems: Architecture, Algorithms and Implementation Vito Dai Electrical Engineering and Computer Sciences...servers or to redistribute to lists, requires prior specific permission. Data Compression for Maskless Lithography Systems: Architecture, Algorithms and...for Maskless Lithography Systems: Architecture, Algorithms and Implementation Copyright 2008 by Vito Dai 1 Abstract Data Compression for Maskless

The Use of Software Agents for Autonomous Control of a DC Space Power System

NASA Technical Reports Server (NTRS)

May, Ryan D.; Loparo, Kenneth A.

2014-01-01

In order to enable manned deep-space missions, the spacecraft must be controlled autonomously using on-board algorithms. A control architecture is proposed to enable this autonomous operation for an spacecraft electric power system and then implemented using a highly distributed network of software agents. These agents collaborate and compete with each other in order to implement each of the control functions. A subset of this control architecture is tested against a steadystate power system simulation and found to be able to solve a constrained optimization problem with competing objectives using only local information.

Towards Internet QoS provisioning based on generic distributed QoS adaptive routing engine.

PubMed

Haikal, Amira Y; Badawy, M; Ali, Hesham A

2014-01-01

Increasing efficiency and quality demands of modern Internet technologies drive today's network engineers to seek to provide quality of service (QoS). Internet QoS provisioning gives rise to several challenging issues. This paper introduces a generic distributed QoS adaptive routing engine (DQARE) architecture based on OSPFxQoS. The innovation of the proposed work in this paper is its undependability on the used QoS architectures and, moreover, splitting of the control strategy from data forwarding mechanisms, so we guarantee a set of absolute stable mechanisms on top of which Internet QoS can be built. DQARE architecture is furnished with three relevant traffic control schemes, namely, service differentiation, QoS routing, and traffic engineering. The main objective of this paper is to (i) provide a general configuration guideline for service differentiation, (ii) formalize the theoretical properties of different QoS routing algorithms and then introduce a QoS routing algorithm (QOPRA) based on dynamic programming technique, and (iii) propose QoS multipath forwarding (QMPF) model for paths diversity exploitation. NS2-based simulations proved the DQARE superiority in terms of delay, packet delivery ratio, throughput, and control overhead. Moreover, extensive simulations are used to compare the proposed QOPRA algorithm and QMPF model with their counterparts in the literature.

Towards Internet QoS Provisioning Based on Generic Distributed QoS Adaptive Routing Engine

PubMed Central

Haikal, Amira Y.; Badawy, M.; Ali, Hesham A.

2014-01-01

Increasing efficiency and quality demands of modern Internet technologies drive today's network engineers to seek to provide quality of service (QoS). Internet QoS provisioning gives rise to several challenging issues. This paper introduces a generic distributed QoS adaptive routing engine (DQARE) architecture based on OSPFxQoS. The innovation of the proposed work in this paper is its undependability on the used QoS architectures and, moreover, splitting of the control strategy from data forwarding mechanisms, so we guarantee a set of absolute stable mechanisms on top of which Internet QoS can be built. DQARE architecture is furnished with three relevant traffic control schemes, namely, service differentiation, QoS routing, and traffic engineering. The main objective of this paper is to (i) provide a general configuration guideline for service differentiation, (ii) formalize the theoretical properties of different QoS routing algorithms and then introduce a QoS routing algorithm (QOPRA) based on dynamic programming technique, and (iii) propose QoS multipath forwarding (QMPF) model for paths diversity exploitation. NS2-based simulations proved the DQARE superiority in terms of delay, packet delivery ratio, throughput, and control overhead. Moreover, extensive simulations are used to compare the proposed QOPRA algorithm and QMPF model with their counterparts in the literature. PMID:25309955

Diagnosis and prediction of periodontally compromised teeth using a deep learning-based convolutional neural network algorithm.

PubMed

Lee, Jae-Hong; Kim, Do-Hyung; Jeong, Seong-Nyum; Choi, Seong-Ho

2018-04-01

The aim of the current study was to develop a computer-assisted detection system based on a deep convolutional neural network (CNN) algorithm and to evaluate the potential usefulness and accuracy of this system for the diagnosis and prediction of periodontally compromised teeth (PCT). Combining pretrained deep CNN architecture and a self-trained network, periapical radiographic images were used to determine the optimal CNN algorithm and weights. The diagnostic and predictive accuracy, sensitivity, specificity, positive predictive value, negative predictive value, receiver operating characteristic (ROC) curve, area under the ROC curve, confusion matrix, and 95% confidence intervals (CIs) were calculated using our deep CNN algorithm, based on a Keras framework in Python. The periapical radiographic dataset was split into training (n=1,044), validation (n=348), and test (n=348) datasets. With the deep learning algorithm, the diagnostic accuracy for PCT was 81.0% for premolars and 76.7% for molars. Using 64 premolars and 64 molars that were clinically diagnosed as severe PCT, the accuracy of predicting extraction was 82.8% (95% CI, 70.1%-91.2%) for premolars and 73.4% (95% CI, 59.9%-84.0%) for molars. We demonstrated that the deep CNN algorithm was useful for assessing the diagnosis and predictability of PCT. Therefore, with further optimization of the PCT dataset and improvements in the algorithm, a computer-aided detection system can be expected to become an effective and efficient method of diagnosing and predicting PCT.

Neural network fusion capabilities for efficient implementation of tracking algorithms

NASA Astrophysics Data System (ADS)

Sundareshan, Malur K.; Amoozegar, Farid

1997-03-01

The ability to efficiently fuse information of different forms to facilitate intelligent decision making is one of the major capabilities of trained multilayer neural networks that is now being recognized. While development of innovative adaptive control algorithms for nonlinear dynamical plants that attempt to exploit these capabilities seems to be more popular, a corresponding development of nonlinear estimation algorithms using these approaches, particularly for application in target surveillance and guidance operations, has not received similar attention. We describe the capabilities and functionality of neural network algorithms for data fusion and implementation of tracking filters. To discuss details and to serve as a vehicle for quantitative performance evaluations, the illustrative case of estimating the position and velocity of surveillance targets is considered. Efficient target- tracking algorithms that can utilize data from a host of sensing modalities and are capable of reliably tracking even uncooperative targets executing fast and complex maneuvers are of interest in a number of applications. The primary motivation for employing neural networks in these applications comes from the efficiency with which more features extracted from different sensor measurements can be utilized as inputs for estimating target maneuvers. A system architecture that efficiently integrates the fusion capabilities of a trained multilayer neural net with the tracking performance of a Kalman filter is described. The innovation lies in the way the fusion of multisensor data is accomplished to facilitate improved estimation without increasing the computational complexity of the dynamical state estimator itself.

Online learning algorithm for time series forecasting suitable for low cost wireless sensor networks nodes.

PubMed

Pardo, Juan; Zamora-Martínez, Francisco; Botella-Rocamora, Paloma

2015-04-21

Time series forecasting is an important predictive methodology which can be applied to a wide range of problems. Particularly, forecasting the indoor temperature permits an improved utilization of the HVAC (Heating, Ventilating and Air Conditioning) systems in a home and thus a better energy efficiency. With such purpose the paper describes how to implement an Artificial Neural Network (ANN) algorithm in a low cost system-on-chip to develop an autonomous intelligent wireless sensor network. The present paper uses a Wireless Sensor Networks (WSN) to monitor and forecast the indoor temperature in a smart home, based on low resources and cost microcontroller technology as the 8051MCU. An on-line learning approach, based on Back-Propagation (BP) algorithm for ANNs, has been developed for real-time time series learning. It performs the model training with every new data that arrive to the system, without saving enormous quantities of data to create a historical database as usual, i.e., without previous knowledge. Consequently to validate the approach a simulation study through a Bayesian baseline model have been tested in order to compare with a database of a real application aiming to see the performance and accuracy. The core of the paper is a new algorithm, based on the BP one, which has been described in detail, and the challenge was how to implement a computational demanding algorithm in a simple architecture with very few hardware resources.

Online Learning Algorithm for Time Series Forecasting Suitable for Low Cost Wireless Sensor Networks Nodes

PubMed Central

Pardo, Juan; Zamora-Martínez, Francisco; Botella-Rocamora, Paloma

2015-01-01

Time series forecasting is an important predictive methodology which can be applied to a wide range of problems. Particularly, forecasting the indoor temperature permits an improved utilization of the HVAC (Heating, Ventilating and Air Conditioning) systems in a home and thus a better energy efficiency. With such purpose the paper describes how to implement an Artificial Neural Network (ANN) algorithm in a low cost system-on-chip to develop an autonomous intelligent wireless sensor network. The present paper uses a Wireless Sensor Networks (WSN) to monitor and forecast the indoor temperature in a smart home, based on low resources and cost microcontroller technology as the 8051MCU. An on-line learning approach, based on Back-Propagation (BP) algorithm for ANNs, has been developed for real-time time series learning. It performs the model training with every new data that arrive to the system, without saving enormous quantities of data to create a historical database as usual, i.e., without previous knowledge. Consequently to validate the approach a simulation study through a Bayesian baseline model have been tested in order to compare with a database of a real application aiming to see the performance and accuracy. The core of the paper is a new algorithm, based on the BP one, which has been described in detail, and the challenge was how to implement a computational demanding algorithm in a simple architecture with very few hardware resources. PMID:25905698

Neural network fusion capabilities for efficient implementation of tracking algorithms

NASA Astrophysics Data System (ADS)

Sundareshan, Malur K.; Amoozegar, Farid

1996-05-01

The ability to efficiently fuse information of different forms for facilitating intelligent decision-making is one of the major capabilities of trained multilayer neural networks that is being recognized int eh recent times. While development of innovative adaptive control algorithms for nonlinear dynamical plants which attempt to exploit these capabilities seems to be more popular, a corresponding development of nonlinear estimation algorithms using these approaches, particularly for application in target surveillance and guidance operations, has not received similar attention. In this paper we describe the capabilities and functionality of neural network algorithms for data fusion and implementation of nonlinear tracking filters. For a discussion of details and for serving as a vehicle for quantitative performance evaluations, the illustrative case of estimating the position and velocity of surveillance targets is considered. Efficient target tracking algorithms that can utilize data from a host of sensing modalities and are capable of reliably tracking even uncooperative targets executing fast and complex maneuvers are of interest in a number of applications. The primary motivation for employing neural networks in these applications comes form the efficiency with which more features extracted from different sensor measurements can be utilized as inputs for estimating target maneuvers. Such an approach results in an overall nonlinear tracking filter which has several advantages over the popular efforts at designing nonlinear estimation algorithms for tracking applications, the principle one being the reduction of mathematical and computational complexities. A system architecture that efficiently integrates the processing capabilities of a trained multilayer neural net with the tracking performance of a Kalman filter is described in this paper.

Neural networks and applications tutorial

NASA Astrophysics Data System (ADS)

Guyon, I.

1991-09-01

The importance of neural networks has grown dramatically during this decade. While only a few years ago they were primarily of academic interest, now dozens of companies and many universities are investigating the potential use of these systems and products are beginning to appear. The idea of building a machine whose architecture is inspired by that of the brain has roots which go far back in history. Nowadays, technological advances of computers and the availability of custom integrated circuits, permit simulations of hundreds or even thousands of neurons. In conjunction, the growing interest in learning machines, non-linear dynamics and parallel computation spurred renewed attention in artificial neural networks. Many tentative applications have been proposed, including decision systems (associative memories, classifiers, data compressors and optimizers), or parametric models for signal processing purposes (system identification, automatic control, noise canceling, etc.). While they do not always outperform standard methods, neural network approaches are already used in some real world applications for pattern recognition and signal processing tasks. The tutorial is divided into six lectures, that where presented at the Third Graduate Summer Course on Computational Physics (September 3-7, 1990) on Parallel Architectures and Applications, organized by the European Physical Society: (1) Introduction: machine learning and biological computation. (2) Adaptive artificial neurons (perceptron, ADALINE, sigmoid units, etc.): learning rules and implementations. (3) Neural network systems: architectures, learning algorithms. (4) Applications: pattern recognition, signal processing, etc. (5) Elements of learning theory: how to build networks which generalize. (6) A case study: a neural network for on-line recognition of handwritten alphanumeric characters.

Modeling and performance analysis of QoS data

NASA Astrophysics Data System (ADS)

Strzeciwilk, Dariusz; Zuberek, Włodzimierz M.

2016-09-01

The article presents the results of modeling and analysis of data transmission performance on systems that support quality of service. Models are designed and tested, taking into account multiservice network architecture, i.e. supporting the transmission of data related to different classes of traffic. Studied were mechanisms of traffic shaping systems, which are based on the Priority Queuing with an integrated source of data and the various sources of data that is generated. Discussed were the basic problems of the architecture supporting QoS and queuing systems. Designed and built were models based on Petri nets, supported by temporal logics. The use of simulation tools was to verify the mechanisms of shaping traffic with the applied queuing algorithms. It is shown that temporal models of Petri nets can be effectively used in the modeling and analysis of the performance of computer networks.

Context Aware Routing Management Architecture for Airborne Networks

DTIC Science & Technology

2012-03-22

awareness, increased survivability, 2 higher operation tempo , greater lethality, improve speed of command and certain degree of self-synchronization [35...first two sets of experiments. This error model simulates deviations from predetermined routes as well as variations on signal strength for radio...routes computed using Maximum Concurrent Multi-Commodity flow algorithm are not susceptible to rapid topology variations induced by noise. 57 5

Clustering and Flow Conservation Monitoring Tool for Software Defined Networks.

PubMed

Puente Fernández, Jesús Antonio; García Villalba, Luis Javier; Kim, Tai-Hoon

2018-04-03

Prediction systems present some challenges on two fronts: the relation between video quality and observed session features and on the other hand, dynamics changes on the video quality. Software Defined Networks (SDN) is a new concept of network architecture that provides the separation of control plane (controller) and data plane (switches) in network devices. Due to the existence of the southbound interface, it is possible to deploy monitoring tools to obtain the network status and retrieve a statistics collection. Therefore, achieving the most accurate statistics depends on a strategy of monitoring and information requests of network devices. In this paper, we propose an enhanced algorithm for requesting statistics to measure the traffic flow in SDN networks. Such an algorithm is based on grouping network switches in clusters focusing on their number of ports to apply different monitoring techniques. Such grouping occurs by avoiding monitoring queries in network switches with common characteristics and then, by omitting redundant information. In this way, the present proposal decreases the number of monitoring queries to switches, improving the network traffic and preventing the switching overload. We have tested our optimization in a video streaming simulation using different types of videos. The experiments and comparison with traditional monitoring techniques demonstrate the feasibility of our proposal maintaining similar values decreasing the number of queries to the switches.

A Hybrid OFDM-TDM Architecture with Decentralized Dynamic Bandwidth Allocation for PONs

PubMed Central

Cevik, Taner

2013-01-01

One of the major challenges of passive optical networks is to achieve a fair arbitration mechanism that will prevent possible collisions from occurring at the upstream channel when multiple users attempt to access the common fiber at the same time. Therefore, in this study we mainly focus on fair bandwidth allocation among users, and present a hybrid Orthogonal Frequency Division Multiplexed/Time Division Multiplexed architecture with a dynamic bandwidth allocation scheme that provides satisfying service qualities to the users depending on their varying bandwidth requirements. Unnecessary delays in centralized schemes occurring during bandwidth assignment stage are eliminated by utilizing a decentralized approach. Instead of sending bandwidth demands to the optical line terminal (OLT) which is the only competent authority, each optical network unit (ONU) runs the same bandwidth demand determination algorithm. ONUs inform each other via signaling channel about the status of their queues. This information is fed to the bandwidth determination algorithm which is run by each ONU in a distributed manner. Furthermore, Light Load Penalty, which is a phenomenon in optical communications, is mitigated by limiting the amount of bandwidth that an ONU can demand. PMID:24194684

A fully convolutional network for weed mapping of unmanned aerial vehicle (UAV) imagery.

PubMed

Huang, Huasheng; Deng, Jizhong; Lan, Yubin; Yang, Aqing; Deng, Xiaoling; Zhang, Lei

2018-01-01

Appropriate Site Specific Weed Management (SSWM) is crucial to ensure the crop yields. Within SSWM of large-scale area, remote sensing is a key technology to provide accurate weed distribution information. Compared with satellite and piloted aircraft remote sensing, unmanned aerial vehicle (UAV) is capable of capturing high spatial resolution imagery, which will provide more detailed information for weed mapping. The objective of this paper is to generate an accurate weed cover map based on UAV imagery. The UAV RGB imagery was collected in 2017 October over the rice field located in South China. The Fully Convolutional Network (FCN) method was proposed for weed mapping of the collected imagery. Transfer learning was used to improve generalization capability, and skip architecture was applied to increase the prediction accuracy. After that, the performance of FCN architecture was compared with Patch_based CNN algorithm and Pixel_based CNN method. Experimental results showed that our FCN method outperformed others, both in terms of accuracy and efficiency. The overall accuracy of the FCN approach was up to 0.935 and the accuracy for weed recognition was 0.883, which means that this algorithm is capable of generating accurate weed cover maps for the evaluated UAV imagery.

Quantum neural network-based EEG filtering for a brain-computer interface.

PubMed

Gandhi, Vaibhav; Prasad, Girijesh; Coyle, Damien; Behera, Laxmidhar; McGinnity, Thomas Martin

2014-02-01

A novel neural information processing architecture inspired by quantum mechanics and incorporating the well-known Schrodinger wave equation is proposed in this paper. The proposed architecture referred to as recurrent quantum neural network (RQNN) can characterize a nonstationary stochastic signal as time-varying wave packets. A robust unsupervised learning algorithm enables the RQNN to effectively capture the statistical behavior of the input signal and facilitates the estimation of signal embedded in noise with unknown characteristics. The results from a number of benchmark tests show that simple signals such as dc, staircase dc, and sinusoidal signals embedded within high noise can be accurately filtered and particle swarm optimization can be employed to select model parameters. The RQNN filtering procedure is applied in a two-class motor imagery-based brain-computer interface where the objective was to filter electroencephalogram (EEG) signals before feature extraction and classification to increase signal separability. A two-step inner-outer fivefold cross-validation approach is utilized to select the algorithm parameters subject-specifically for nine subjects. It is shown that the subject-specific RQNN EEG filtering significantly improves brain-computer interface performance compared to using only the raw EEG or Savitzky-Golay filtered EEG across multiple sessions.

Fast converging minimum probability of error neural network receivers for DS-CDMA communications.

PubMed

Matyjas, John D; Psaromiligkos, Ioannis N; Batalama, Stella N; Medley, Michael J

2004-03-01

We consider a multilayer perceptron neural network (NN) receiver architecture for the recovery of the information bits of a direct-sequence code-division-multiple-access (DS-CDMA) user. We develop a fast converging adaptive training algorithm that minimizes the bit-error rate (BER) at the output of the receiver. The adaptive algorithm has three key features: i) it incorporates the BER, i.e., the ultimate performance evaluation measure, directly into the learning process, ii) it utilizes constraints that are derived from the properties of the optimum single-user decision boundary for additive white Gaussian noise (AWGN) multiple-access channels, and iii) it embeds importance sampling (IS) principles directly into the receiver optimization process. Simulation studies illustrate the BER performance of the proposed scheme.

Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks

PubMed Central

Yu, Haiyang; Wu, Zhihai; Wang, Shuqin; Wang, Yunpeng; Ma, Xiaolei

2017-01-01

Predicting large-scale transportation network traffic has become an important and challenging topic in recent decades. Inspired by the domain knowledge of motion prediction, in which the future motion of an object can be predicted based on previous scenes, we propose a network grid representation method that can retain the fine-scale structure of a transportation network. Network-wide traffic speeds are converted into a series of static images and input into a novel deep architecture, namely, spatiotemporal recurrent convolutional networks (SRCNs), for traffic forecasting. The proposed SRCNs inherit the advantages of deep convolutional neural networks (DCNNs) and long short-term memory (LSTM) neural networks. The spatial dependencies of network-wide traffic can be captured by DCNNs, and the temporal dynamics can be learned by LSTMs. An experiment on a Beijing transportation network with 278 links demonstrates that SRCNs outperform other deep learning-based algorithms in both short-term and long-term traffic prediction. PMID:28672867

Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks.

PubMed

Yu, Haiyang; Wu, Zhihai; Wang, Shuqin; Wang, Yunpeng; Ma, Xiaolei

2017-06-26

Predicting large-scale transportation network traffic has become an important and challenging topic in recent decades. Inspired by the domain knowledge of motion prediction, in which the future motion of an object can be predicted based on previous scenes, we propose a network grid representation method that can retain the fine-scale structure of a transportation network. Network-wide traffic speeds are converted into a series of static images and input into a novel deep architecture, namely, spatiotemporal recurrent convolutional networks (SRCNs), for traffic forecasting. The proposed SRCNs inherit the advantages of deep convolutional neural networks (DCNNs) and long short-term memory (LSTM) neural networks. The spatial dependencies of network-wide traffic can be captured by DCNNs, and the temporal dynamics can be learned by LSTMs. An experiment on a Beijing transportation network with 278 links demonstrates that SRCNs outperform other deep learning-based algorithms in both short-term and long-term traffic prediction.

Control of magnetic bearing systems via the Chebyshev polynomial-based unified model (CPBUM) neural network.

PubMed

Jeng, J T; Lee, T T

2000-01-01

A Chebyshev polynomial-based unified model (CPBUM) neural network is introduced and applied to control a magnetic bearing systems. First, we show that the CPBUM neural network not only has the same capability of universal approximator, but also has faster learning speed than conventional feedforward/recurrent neural network. It turns out that the CPBUM neural network is more suitable in the design of controller than the conventional feedforward/recurrent neural network. Second, we propose the inverse system method, based on the CPBUM neural networks, to control a magnetic bearing system. The proposed controller has two structures; namely, off-line and on-line learning structures. We derive a new learning algorithm for each proposed structure. The experimental results show that the proposed neural network architecture provides a greater flexibility and better performance in controlling magnetic bearing systems.

GLOBECOM '88 - IEEE Global Telecommunications Conference and Exhibition, Hollywood, FL, Nov. 28-Dec. 1, 1988, Conference Record. Volumes 1, 2, & 3

NASA Astrophysics Data System (ADS)

Various papers on communications for the information age are presented. Among the general topics considered are: telematic services and terminals, satellite communications, telecommunications mangaement network, control of integrated broadband networks, advances in digital radio systems, the intelligent network, broadband networks and services deployment, future switch architectures, performance analysis of computer networks, advances in spread spectrum, optical high-speed LANs, and broadband switching and networks. Also addressed are: multiple access protocols, video coding techniques, modulation and coding, photonic switching, SONET terminals and applications, standards for video coding, digital switching, progress in MANs, mobile and portable radio, software design for improved maintainability, multipath propagation and advanced countermeasure, data communication, network control and management, fiber in the loop, network algorithm and protocols, and advances in computer communications.

Intelligent neural network and fuzzy logic control of industrial and power systems

NASA Astrophysics Data System (ADS)

Kuljaca, Ognjen

The main role played by neural network and fuzzy logic intelligent control algorithms today is to identify and compensate unknown nonlinear system dynamics. There are a number of methods developed, but often the stability analysis of neural network and fuzzy control systems was not provided. This work will meet those problems for the several algorithms. Some more complicated control algorithms included backstepping and adaptive critics will be designed. Nonlinear fuzzy control with nonadaptive fuzzy controllers is also analyzed. An experimental method for determining describing function of SISO fuzzy controller is given. The adaptive neural network tracking controller for an autonomous underwater vehicle is analyzed. A novel stability proof is provided. The implementation of the backstepping neural network controller for the coupled motor drives is described. Analysis and synthesis of adaptive critic neural network control is also provided in the work. Novel tuning laws for the system with action generating neural network and adaptive fuzzy critic are given. Stability proofs are derived for all those control methods. It is shown how these control algorithms and approaches can be used in practical engineering control. Stability proofs are given. Adaptive fuzzy logic control is analyzed. Simulation study is conducted to analyze the behavior of the adaptive fuzzy system on the different environment changes. A novel stability proof for adaptive fuzzy logic systems is given. Also, adaptive elastic fuzzy logic control architecture is described and analyzed. A novel membership function is used for elastic fuzzy logic system. The stability proof is proffered. Adaptive elastic fuzzy logic control is compared with the adaptive nonelastic fuzzy logic control. The work described in this dissertation serves as foundation on which analysis of particular representative industrial systems will be conducted. Also, it gives a good starting point for analysis of learning abilities of adaptive and neural network control systems, as well as for the analysis of the different algorithms such as elastic fuzzy systems.

Iterative User-Centered Design of a Next Generation Patient Monitoring System for Emergency Medical Response

PubMed Central

Gao, Tia; Kim, Matthew I.; White, David; Alm, Alexander M.

2006-01-01

We have developed a system for real-time patient monitoring during large-scale disasters. Our system is designed with scalable algorithms to monitor large numbers of patients, an intuitive interface to support the overwhelmed responders, and ad-hoc mesh networking capabilities to maintain connectivity to patients in the chaotic settings. This paper describes an iterative approach to user-centered design adopted to guide development of our system. This system is a part of the Advanced Health and Disaster Aid Network (AID-N) architecture. PMID:17238348

Implementation of a Space Communications Cognitive Engine

NASA Technical Reports Server (NTRS)

Hackett, Timothy M.; Bilen, Sven G.; Ferreira, Paulo Victor R.; Wyglinski, Alexander M.; Reinhart, Richard C.

2017-01-01

Although communications-based cognitive engines have been proposed, very few have been implemented in a full system, especially in a space communications system. In this paper, we detail the implementation of a multi-objective reinforcement-learning algorithm and deep artificial neural networks for the use as a radio-resource-allocation controller. The modular software architecture presented encourages re-use and easy modification for trying different algorithms. Various trade studies involved with the system implementation and integration are discussed. These include the choice of software libraries that provide platform flexibility and promote reusability, choices regarding the deployment of this cognitive engine within a system architecture using the DVB-S2 standard and commercial hardware, and constraints placed on the cognitive engine caused by real-world radio constraints. The implemented radio-resource allocation-management controller was then integrated with the larger spaceground system developed by NASA Glenn Research Center (GRC).

Job Scheduling in a Heterogeneous Grid Environment

NASA Technical Reports Server (NTRS)

Shan, Hong-Zhang; Smith, Warren; Oliker, Leonid; Biswas, Rupak

2004-01-01

Computational grids have the potential for solving large-scale scientific problems using heterogeneous and geographically distributed resources. However, a number of major technical hurdles must be overcome before this potential can be realized. One problem that is critical to effective utilization of computational grids is the efficient scheduling of jobs. This work addresses this problem by describing and evaluating a grid scheduling architecture and three job migration algorithms. The architecture is scalable and does not assume control of local site resources. The job migration policies use the availability and performance of computer systems, the network bandwidth available between systems, and the volume of input and output data associated with each job. An extensive performance comparison is presented using real workloads from leading computational centers. The results, based on several key metrics, demonstrate that the performance of our distributed migration algorithms is significantly greater than that of a local scheduling framework and comparable to a non-scalable global scheduling approach.

A system for routing arbitrary directed graphs on SIMD architectures

NASA Technical Reports Server (NTRS)

Tomboulian, Sherryl

1987-01-01

There are many problems which can be described in terms of directed graphs that contain a large number of vertices where simple computations occur using data from connecting vertices. A method is given for parallelizing such problems on an SIMD machine model that is bit-serial and uses only nearest neighbor connections for communication. Each vertex of the graph will be assigned to a processor in the machine. Algorithms are given that will be used to implement movement of data along the arcs of the graph. This architecture and algorithms define a system that is relatively simple to build and can do graph processing. All arcs can be transversed in parallel in time O(T), where T is empirically proportional to the diameter of the interconnection network times the average degree of the graph. Modifying or adding a new arc takes the same time as parallel traversal.

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].

Minimal perceptrons for memorizing complex patterns

NASA Astrophysics Data System (ADS)

Pastor, Marissa; Song, Juyong; Hoang, Danh-Tai; Jo, Junghyo

2016-11-01

Feedforward neural networks have been investigated to understand learning and memory, as well as applied to numerous practical problems in pattern classification. It is a rule of thumb that more complex tasks require larger networks. However, the design of optimal network architectures for specific tasks is still an unsolved fundamental problem. In this study, we consider three-layered neural networks for memorizing binary patterns. We developed a new complexity measure of binary patterns, and estimated the minimal network size for memorizing them as a function of their complexity. We formulated the minimal network size for regular, random, and complex patterns. In particular, the minimal size for complex patterns, which are neither ordered nor disordered, was predicted by measuring their Hamming distances from known ordered patterns. Our predictions agree with simulations based on the back-propagation algorithm.

Facial Expression Recognition with Fusion Features Extracted from Salient Facial Areas.

PubMed

Liu, Yanpeng; Li, Yibin; Ma, Xin; Song, Rui

2017-03-29

In the pattern recognition domain, deep architectures are currently widely used and they have achieved fine results. However, these deep architectures make particular demands, especially in terms of their requirement for big datasets and GPU. Aiming to gain better results without deep networks, we propose a simplified algorithm framework using fusion features extracted from the salient areas of faces. Furthermore, the proposed algorithm has achieved a better result than some deep architectures. For extracting more effective features, this paper firstly defines the salient areas on the faces. This paper normalizes the salient areas of the same location in the faces to the same size; therefore, it can extracts more similar features from different subjects. LBP and HOG features are extracted from the salient areas, fusion features' dimensions are reduced by Principal Component Analysis (PCA) and we apply several classifiers to classify the six basic expressions at once. This paper proposes a salient areas definitude method which uses peak expressions frames compared with neutral faces. This paper also proposes and applies the idea of normalizing the salient areas to align the specific areas which express the different expressions. As a result, the salient areas found from different subjects are the same size. In addition, the gamma correction method is firstly applied on LBP features in our algorithm framework which improves our recognition rates significantly. By applying this algorithm framework, our research has gained state-of-the-art performances on CK+ database and JAFFE database.

Livermore Big Artificial Neural Network Toolkit

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

Essen, Brian Van; Jacobs, Sam; Kim, Hyojin

2016-07-01

LBANN is a toolkit that is designed to train artificial neural networks efficiently on high performance computing architectures. It is optimized to take advantages of key High Performance Computing features to accelerate neural network training. Specifically it is optimized for low-latency, high bandwidth interconnects, node-local NVRAM, node-local GPU accelerators, and high bandwidth parallel file systems. It is built on top of the open source Elemental distributed-memory dense and spars-direct linear algebra and optimization library that is released under the BSD license. The algorithms contained within LBANN are drawn from the academic literature and implemented to work within a distributed-memory framework.

A Faster Parallel Algorithm and Efficient Multithreaded Implementations for Evaluating Betweenness Centrality on Massive Datasets

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

Madduri, Kamesh; Ediger, David; Jiang, Karl

2009-05-29

We present a new lock-free parallel algorithm for computing betweenness centrality of massive small-world networks. With minor changes to the data structures, our algorithm also achieves better spatial cache locality compared to previous approaches. Betweenness centrality is a key algorithm kernel in the HPCS SSCA#2 Graph Analysis benchmark, which has been extensively used to evaluate the performance of emerging high-performance computing architectures for graph-theoretic computations. We design optimized implementations of betweenness centrality and the SSCA#2 benchmark for two hardware multithreaded systems: a Cray XMT system with the ThreadStorm processor, and a single-socket Sun multicore server with the UltraSparc T2 processor.more » For a small-world network of 134 million vertices and 1.073 billion edges, the 16-processor XMT system and the 8-core Sun Fire T5120 server achieve TEPS scores (an algorithmic performance count for the SSCA#2 benchmark) of 160 million and 90 million respectively, which corresponds to more than a 2X performance improvement over the previous parallel implementations. To better characterize the performance of these multithreaded systems, we correlate the SSCA#2 performance results with data from the memory-intensive STREAM and RandomAccess benchmarks. Finally, we demonstrate the applicability of our implementation to analyze massive real-world datasets by computing approximate betweenness centrality for a large-scale IMDb movie-actor network.« less

Autonomous self-configuration of artificial neural networks for data classification or system control

NASA Astrophysics Data System (ADS)

Fink, Wolfgang

2009-05-01

Artificial neural networks (ANNs) are powerful methods for the classification of multi-dimensional data as well as for the control of dynamic systems. In general terms, ANNs consist of neurons that are, e.g., arranged in layers and interconnected by real-valued or binary neural couplings or weights. ANNs try mimicking the processing taking place in biological brains. The classification and generalization capabilities of ANNs are given by the interconnection architecture and the coupling strengths. To perform a certain classification or control task with a particular ANN architecture (i.e., number of neurons, number of layers, etc.), the inter-neuron couplings and their accordant coupling strengths must be determined (1) either by a priori design (i.e., manually) or (2) using training algorithms such as error back-propagation. The more complex the classification or control task, the less obvious it is how to determine an a priori design of an ANN, and, as a consequence, the architecture choice becomes somewhat arbitrary. Furthermore, rather than being able to determine for a given architecture directly the corresponding coupling strengths necessary to perform the classification or control task, these have to be obtained/learned through training of the ANN on test data. We report on the use of a Stochastic Optimization Framework (SOF; Fink, SPIE 2008) for the autonomous self-configuration of Artificial Neural Networks (i.e., the determination of number of hidden layers, number of neurons per hidden layer, interconnections between neurons, and respective coupling strengths) for performing classification or control tasks. This may provide an approach towards cognizant and self-adapting computing architectures and systems.

A Deep Learning Algorithm for Prediction of Age-Related Eye Disease Study Severity Scale for Age-Related Macular Degeneration from Color Fundus Photography.

PubMed

Grassmann, Felix; Mengelkamp, Judith; Brandl, Caroline; Harsch, Sebastian; Zimmermann, Martina E; Linkohr, Birgit; Peters, Annette; Heid, Iris M; Palm, Christoph; Weber, Bernhard H F

2018-04-10

Age-related macular degeneration (AMD) is a common threat to vision. While classification of disease stages is critical to understanding disease risk and progression, several systems based on color fundus photographs are known. Most of these require in-depth and time-consuming analysis of fundus images. Herein, we present an automated computer-based classification algorithm. Algorithm development for AMD classification based on a large collection of color fundus images. Validation is performed on a cross-sectional, population-based study. We included 120 656 manually graded color fundus images from 3654 Age-Related Eye Disease Study (AREDS) participants. AREDS participants were >55 years of age, and non-AMD sight-threatening diseases were excluded at recruitment. In addition, performance of our algorithm was evaluated in 5555 fundus images from the population-based Kooperative Gesundheitsforschung in der Region Augsburg (KORA; Cooperative Health Research in the Region of Augsburg) study. We defined 13 classes (9 AREDS steps, 3 late AMD stages, and 1 for ungradable images) and trained several convolution deep learning architectures. An ensemble of network architectures improved prediction accuracy. An independent dataset was used to evaluate the performance of our algorithm in a population-based study. κ Statistics and accuracy to evaluate the concordance between predicted and expert human grader classification. A network ensemble of 6 different neural net architectures predicted the 13 classes in the AREDS test set with a quadratic weighted κ of 92% (95% confidence interval, 89%-92%) and an overall accuracy of 63.3%. In the independent KORA dataset, images wrongly classified as AMD were mainly the result of a macular reflex observed in young individuals. By restricting the KORA analysis to individuals >55 years of age and prior exclusion of other retinopathies, the weighted and unweighted κ increased to 50% and 63%, respectively. Importantly, the algorithm detected 84.2% of all fundus images with definite signs of early or late AMD. Overall, 94.3% of healthy fundus images were classified correctly. Our deep learning algoritm revealed a weighted κ outperforming human graders in the AREDS study and is suitable to classify AMD fundus images in other datasets using individuals >55 years of age. Copyright © 2018 American Academy of Ophthalmology. Published by Elsevier Inc. All rights reserved.

Digital optical computers at the optoelectronic computing systems center

NASA Technical Reports Server (NTRS)

Jordan, Harry F.

1991-01-01

The Digital Optical Computing Program within the National Science Foundation Engineering Research Center for Opto-electronic Computing Systems has as its specific goal research on optical computing architectures suitable for use at the highest possible speeds. The program can be targeted toward exploiting the time domain because other programs in the Center are pursuing research on parallel optical systems, exploiting optical interconnection and optical devices and materials. Using a general purpose computing architecture as the focus, we are developing design techniques, tools and architecture for operation at the speed of light limit. Experimental work is being done with the somewhat low speed components currently available but with architectures which will scale up in speed as faster devices are developed. The design algorithms and tools developed for a general purpose, stored program computer are being applied to other systems such as optimally controlled optical communication networks.

Blur identification by multilayer neural network based on multivalued neurons.

PubMed

Aizenberg, Igor; Paliy, Dmitriy V; Zurada, Jacek M; Astola, Jaakko T

2008-05-01

A multilayer neural network based on multivalued neurons (MLMVN) is a neural network with a traditional feedforward architecture. At the same time, this network has a number of specific different features. Its backpropagation learning algorithm is derivative-free. The functionality of MLMVN is superior to that of the traditional feedforward neural networks and of a variety kernel-based networks. Its higher flexibility and faster adaptation to the target mapping enables to model complex problems using simpler networks. In this paper, the MLMVN is used to identify both type and parameters of the point spread function, whose precise identification is of crucial importance for the image deblurring. The simulation results show the high efficiency of the proposed approach. It is confirmed that the MLMVN is a powerful tool for solving classification problems, especially multiclass ones.

Radio Synthesis Imaging - A High Performance Computing and Communications Project

NASA Astrophysics Data System (ADS)

Crutcher, Richard M.

The National Science Foundation has funded a five-year High Performance Computing and Communications project at the National Center for Supercomputing Applications (NCSA) for the direct implementation of several of the computing recommendations of the Astronomy and Astrophysics Survey Committee (the "Bahcall report"). This paper is a summary of the project goals and a progress report. The project will implement a prototype of the next generation of astronomical telescope systems - remotely located telescopes connected by high-speed networks to very high performance, scalable architecture computers and on-line data archives, which are accessed by astronomers over Gbit/sec networks. Specifically, a data link has been installed between the BIMA millimeter-wave synthesis array at Hat Creek, California and NCSA at Urbana, Illinois for real-time transmission of data to NCSA. Data are automatically archived, and may be browsed and retrieved by astronomers using the NCSA Mosaic software. In addition, an on-line digital library of processed images will be established. BIMA data will be processed on a very high performance distributed computing system, with I/O, user interface, and most of the software system running on the NCSA Convex C3880 supercomputer or Silicon Graphics Onyx workstations connected by HiPPI to the high performance, massively parallel Thinking Machines Corporation CM-5. The very computationally intensive algorithms for calibration and imaging of radio synthesis array observations will be optimized for the CM-5 and new algorithms which utilize the massively parallel architecture will be developed. Code running simultaneously on the distributed computers will communicate using the Data Transport Mechanism developed by NCSA. The project will also use the BLANCA Gbit/s testbed network between Urbana and Madison, Wisconsin to connect an Onyx workstation in the University of Wisconsin Astronomy Department to the NCSA CM-5, for development of long-distance distributed computing. Finally, the project is developing 2D and 3D visualization software as part of the international AIPS++ project. This research and development project is being carried out by a team of experts in radio astronomy, algorithm development for massively parallel architectures, high-speed networking, database management, and Thinking Machines Corporation personnel. The development of this complete software, distributed computing, and data archive and library solution to the radio astronomy computing problem will advance our expertise in high performance computing and communications technology and the application of these techniques to astronomical data processing.

Content addressable memory project

NASA Technical Reports Server (NTRS)

Hall, J. Storrs; Levy, Saul; Smith, Donald E.; Miyake, Keith M.

1992-01-01

A parameterized version of the tree processor was designed and tested (by simulation). The leaf processor design is 90 percent complete. We expect to complete and test a combination of tree and leaf cell designs in the next period. Work is proceeding on algorithms for the computer aided manufacturing (CAM), and once the design is complete we will begin simulating algorithms for large problems. The following topics are covered: (1) the practical implementation of content addressable memory; (2) design of a LEAF cell for the Rutgers CAM architecture; (3) a circuit design tool user's manual; and (4) design and analysis of efficient hierarchical interconnection networks.

Processing large remote sensing image data sets on Beowulf clusters

USGS Publications Warehouse

Steinwand, Daniel R.; Maddox, Brian; Beckmann, Tim; Schmidt, Gail

2003-01-01

High-performance computing is often concerned with the speed at which floating- point calculations can be performed. The architectures of many parallel computers and/or their network topologies are based on these investigations. Often, benchmarks resulting from these investigations are compiled with little regard to how a large dataset would move about in these systems. This part of the Beowulf study addresses that concern by looking at specific applications software and system-level modifications. Applications include an implementation of a smoothing filter for time-series data, a parallel implementation of the decision tree algorithm used in the Landcover Characterization project, a parallel Kriging algorithm used to fit point data collected in the field on invasive species to a regular grid, and modifications to the Beowulf project's resampling algorithm to handle larger, higher resolution datasets at a national scale. Systems-level investigations include a feasibility study on Flat Neighborhood Networks and modifications of that concept with Parallel File Systems.

The Incremental Multiresolution Matrix Factorization Algorithm

PubMed Central

Ithapu, Vamsi K.; Kondor, Risi; Johnson, Sterling C.; Singh, Vikas

2017-01-01

Multiresolution analysis and matrix factorization are foundational tools in computer vision. In this work, we study the interface between these two distinct topics and obtain techniques to uncover hierarchical block structure in symmetric matrices – an important aspect in the success of many vision problems. Our new algorithm, the incremental multiresolution matrix factorization, uncovers such structure one feature at a time, and hence scales well to large matrices. We describe how this multiscale analysis goes much farther than what a direct “global” factorization of the data can identify. We evaluate the efficacy of the resulting factorizations for relative leveraging within regression tasks using medical imaging data. We also use the factorization on representations learned by popular deep networks, providing evidence of their ability to infer semantic relationships even when they are not explicitly trained to do so. We show that this algorithm can be used as an exploratory tool to improve the network architecture, and within numerous other settings in vision. PMID:29416293

Secure smart grid communications and information integration based on digital watermarking in wireless sensor networks

NASA Astrophysics Data System (ADS)

Yan, Xin; Zhang, Ling; Wu, Yang; Luo, Youlong; Zhang, Xiaoxing

2017-02-01

As more and more wireless sensor nodes and networks are employed to acquire and transmit the state information of power equipment in smart grid, we are in urgent need of some viable security solutions to ensure secure smart grid communications. Conventional information security solutions, such as encryption/decryption, digital signature and so forth, are not applicable to wireless sensor networks in smart grid any longer, where bulk messages need to be exchanged continuously. The reason is that these cryptographic solutions will account for a large portion of the extremely limited resources on sensor nodes. In this article, a security solution based on digital watermarking is adopted to achieve the secure communications for wireless sensor networks in smart grid by data and entity authentications at a low cost of operation. Our solution consists of a secure framework of digital watermarking, and two digital watermarking algorithms based on alternating electric current and time window, respectively. Both watermarking algorithms are composed of watermark generation, embedding and detection. The simulation experiments are provided to verify the correctness and practicability of our watermarking algorithms. Additionally, a new cloud-based architecture for the information integration of smart grid is proposed on the basis of our security solutions.

CNN-BLPred: a Convolutional neural network based predictor for β-Lactamases (BL) and their classes.

PubMed

White, Clarence; Ismail, Hamid D; Saigo, Hiroto; Kc, Dukka B

2017-12-28

The β-Lactamase (BL) enzyme family is an important class of enzymes that plays a key role in bacterial resistance to antibiotics. As the newly identified number of BL enzymes is increasing daily, it is imperative to develop a computational tool to classify the newly identified BL enzymes into one of its classes. There are two types of classification of BL enzymes: Molecular Classification and Functional Classification. Existing computational methods only address Molecular Classification and the performance of these existing methods is unsatisfactory. We addressed the unsatisfactory performance of the existing methods by implementing a Deep Learning approach called Convolutional Neural Network (CNN). We developed CNN-BLPred, an approach for the classification of BL proteins. The CNN-BLPred uses Gradient Boosted Feature Selection (GBFS) in order to select the ideal feature set for each BL classification. Based on the rigorous benchmarking of CCN-BLPred using both leave-one-out cross-validation and independent test sets, CCN-BLPred performed better than the other existing algorithms. Compared with other architectures of CNN, Recurrent Neural Network, and Random Forest, the simple CNN architecture with only one convolutional layer performs the best. After feature extraction, we were able to remove ~95% of the 10,912 features using Gradient Boosted Trees. During 10-fold cross validation, we increased the accuracy of the classic BL predictions by 7%. We also increased the accuracy of Class A, Class B, Class C, and Class D performance by an average of 25.64%. The independent test results followed a similar trend. We implemented a deep learning algorithm known as Convolutional Neural Network (CNN) to develop a classifier for BL classification. Combined with feature selection on an exhaustive feature set and using balancing method such as Random Oversampling (ROS), Random Undersampling (RUS) and Synthetic Minority Oversampling Technique (SMOTE), CNN-BLPred performs significantly better than existing algorithms for BL classification.

A high performance long-reach passive optical network with a novel excess bandwidth distribution scheme

NASA Astrophysics Data System (ADS)

Chao, I.-Fen; Zhang, Tsung-Min

2015-06-01

Long-reach passive optical networks (LR-PONs) have been considered to be promising solutions for future access networks. In this paper, we propose a distributed medium access control (MAC) scheme over an advantageous LR-PON network architecture that reroutes the control information from and back to all ONUs through an (N + 1) × (N + 1) star coupler (SC) deployed near the ONUs, thereby overwhelming the extremely long propagation delay problem in LR-PONs. In the network, the control slot is designed to contain all bandwidth requirements of all ONUs and is in-band time-division-multiplexed with a number of data slots within a cycle. In the proposed MAC scheme, a novel profit-weight-based dynamic bandwidth allocation (P-DBA) scheme is presented. The algorithm is designed to efficiently and fairly distribute the amount of excess bandwidth based on a profit value derived from the excess bandwidth usage of each ONU, which resolves the problems of previously reported DBA schemes that are either unfair or inefficient. The simulation results show that the proposed decentralized algorithms exhibit a nearly three-order-of-magnitude improvement in delay performance compared to the centralized algorithms over LR-PONs. Moreover, the newly proposed P-DBA scheme guarantees low delay performance and fairness even when under attack by the malevolent ONU irrespective of traffic loads and burstiness.

A Multi-Hop Energy Neutral Clustering Algorithm for Maximizing Network Information Gathering in Energy Harvesting Wireless Sensor Networks.

PubMed

Yang, Liu; Lu, Yinzhi; Zhong, Yuanchang; Wu, Xuegang; Yang, Simon X

2015-12-26

Energy resource limitation is a severe problem in traditional wireless sensor networks (WSNs) because it restricts the lifetime of network. Recently, the emergence of energy harvesting techniques has brought with them the expectation to overcome this problem. In particular, it is possible for a sensor node with energy harvesting abilities to work perpetually in an Energy Neutral state. In this paper, a Multi-hop Energy Neutral Clustering (MENC) algorithm is proposed to construct the optimal multi-hop clustering architecture in energy harvesting WSNs, with the goal of achieving perpetual network operation. All cluster heads (CHs) in the network act as routers to transmit data to base station (BS) cooperatively by a multi-hop communication method. In addition, by analyzing the energy consumption of intra- and inter-cluster data transmission, we give the energy neutrality constraints. Under these constraints, every sensor node can work in an energy neutral state, which in turn provides perpetual network operation. Furthermore, the minimum network data transmission cycle is mathematically derived using convex optimization techniques while the network information gathering is maximal. Simulation results show that our protocol can achieve perpetual network operation, so that the consistent data delivery is guaranteed. In addition, substantial improvements on the performance of network throughput are also achieved as compared to the famous traditional clustering protocol LEACH and recent energy harvesting aware clustering protocols.

A Multi-Hop Energy Neutral Clustering Algorithm for Maximizing Network Information Gathering in Energy Harvesting Wireless Sensor Networks

PubMed Central

Yang, Liu; Lu, Yinzhi; Zhong, Yuanchang; Wu, Xuegang; Yang, Simon X.

2015-01-01

Energy resource limitation is a severe problem in traditional wireless sensor networks (WSNs) because it restricts the lifetime of network. Recently, the emergence of energy harvesting techniques has brought with them the expectation to overcome this problem. In particular, it is possible for a sensor node with energy harvesting abilities to work perpetually in an Energy Neutral state. In this paper, a Multi-hop Energy Neutral Clustering (MENC) algorithm is proposed to construct the optimal multi-hop clustering architecture in energy harvesting WSNs, with the goal of achieving perpetual network operation. All cluster heads (CHs) in the network act as routers to transmit data to base station (BS) cooperatively by a multi-hop communication method. In addition, by analyzing the energy consumption of intra- and inter-cluster data transmission, we give the energy neutrality constraints. Under these constraints, every sensor node can work in an energy neutral state, which in turn provides perpetual network operation. Furthermore, the minimum network data transmission cycle is mathematically derived using convex optimization techniques while the network information gathering is maximal. Simulation results show that our protocol can achieve perpetual network operation, so that the consistent data delivery is guaranteed. In addition, substantial improvements on the performance of network throughput are also achieved as compared to the famous traditional clustering protocol LEACH and recent energy harvesting aware clustering protocols. PMID:26712764

Fiber-wireless integrated mobile backhaul network based on a hybrid millimeter-wave and free-space-optics architecture with an adaptive diversity combining technique.

PubMed

Zhang, Junwen; Wang, Jing; Xu, Yuming; Xu, Mu; Lu, Feng; Cheng, Lin; Yu, Jianjun; Chang, Gee-Kung

2016-05-01

We propose and experimentally demonstrate a novel fiber-wireless integrated mobile backhaul network based on a hybrid millimeter-wave (MMW) and free-space-optics (FSO) architecture using an adaptive combining technique. Both 60 GHz MMW and FSO links are demonstrated and fully integrated with optical fibers in a scalable and cost-effective backhaul system setup. Joint signal processing with an adaptive diversity combining technique (ADCT) is utilized at the receiver side based on a maximum ratio combining algorithm. Mobile backhaul transportation of 4-Gb/s 16 quadrature amplitude modulation frequency-division multiplexing (QAM-OFDM) data is experimentally demonstrated and tested under various weather conditions synthesized in the lab. Performance improvement in terms of reduced error vector magnitude (EVM) and enhanced link reliability are validated under fog, rain, and turbulence conditions.

Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence

PubMed Central

Cichy, Radoslaw Martin; Khosla, Aditya; Pantazis, Dimitrios; Torralba, Antonio; Oliva, Aude

2016-01-01

The complex multi-stage architecture of cortical visual pathways provides the neural basis for efficient visual object recognition in humans. However, the stage-wise computations therein remain poorly understood. Here, we compared temporal (magnetoencephalography) and spatial (functional MRI) visual brain representations with representations in an artificial deep neural network (DNN) tuned to the statistics of real-world visual recognition. We showed that the DNN captured the stages of human visual processing in both time and space from early visual areas towards the dorsal and ventral streams. Further investigation of crucial DNN parameters revealed that while model architecture was important, training on real-world categorization was necessary to enforce spatio-temporal hierarchical relationships with the brain. Together our results provide an algorithmically informed view on the spatio-temporal dynamics of visual object recognition in the human visual brain. PMID:27282108

Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence.

PubMed

Cichy, Radoslaw Martin; Khosla, Aditya; Pantazis, Dimitrios; Torralba, Antonio; Oliva, Aude

2016-06-10

The complex multi-stage architecture of cortical visual pathways provides the neural basis for efficient visual object recognition in humans. However, the stage-wise computations therein remain poorly understood. Here, we compared temporal (magnetoencephalography) and spatial (functional MRI) visual brain representations with representations in an artificial deep neural network (DNN) tuned to the statistics of real-world visual recognition. We showed that the DNN captured the stages of human visual processing in both time and space from early visual areas towards the dorsal and ventral streams. Further investigation of crucial DNN parameters revealed that while model architecture was important, training on real-world categorization was necessary to enforce spatio-temporal hierarchical relationships with the brain. Together our results provide an algorithmically informed view on the spatio-temporal dynamics of visual object recognition in the human visual brain.

A novel PON based UMTS broadband wireless access network architecture with an algorithm to guarantee end to end QoS

NASA Astrophysics Data System (ADS)

Sana, Ajaz; Hussain, Shahab; Ali, Mohammed A.; Ahmed, Samir

2007-09-01

In this paper we proposes a novel Passive Optical Network (PON) based broadband wireless access network architecture to provide multimedia services (video telephony, video streaming, mobile TV, mobile emails etc) to mobile users. In the conventional wireless access networks, the base stations (Node B) and Radio Network Controllers (RNC) are connected by point to point T1/E1 lines (Iub interface). The T1/E1 lines are expensive and add up to operating costs. Also the resources (transceivers and T1/E1) are designed for peak hours traffic, so most of the time the dedicated resources are idle and wasted. Further more the T1/E1 lines are not capable of supporting bandwidth (BW) required by next generation wireless multimedia services proposed by High Speed Packet Access (HSPA, Rel.5) for Universal Mobile Telecommunications System (UMTS) and Evolution Data only (EV-DO) for Code Division Multiple Access 2000 (CDMA2000). The proposed PON based back haul can provide Giga bit data rates and Iub interface can be dynamically shared by Node Bs. The BW is dynamically allocated and the unused BW from lightly loaded Node Bs is assigned to heavily loaded Node Bs. We also propose a novel algorithm to provide end to end Quality of Service (QoS) (between RNC and user equipment).The algorithm provides QoS bounds in the wired domain as well as in wireless domain with compensation for wireless link errors. Because of the air interface there can be certain times when the user equipment (UE) is unable to communicate with Node B (usually referred to as link error). Since the link errors are bursty and location dependent. For a proposed approach, the scheduler at the Node B maps priorities and weights for QoS into wireless MAC. The compensations for errored links is provided by the swapping of services between the active users and the user data is divided into flows, with flows allowed to lag or lead. The algorithm guarantees (1)delay and throughput for error-free flows,(2)short term fairness among error-free flows,(3)long term fairness among errored and error-free flows,(4)graceful degradation for leading flows and graceful compensation for lagging flows.

Optimum Guidance Law and Information Management for a Large Number of Formation Flying Spacecrafts

NASA Astrophysics Data System (ADS)

Tsuda, Yuichi; Nakasuka, Shinichi

In recent years, formation flying technique is recognized as one of the most important technologies for deep space and orbital missions that involve multiple spacecraft operations. Formation flying mission improves simultaneous observability over a wide area, redundancy and reconfigurability of the system with relatively small and low cost spacecrafts compared with the conventional single spacecraft mission. From the viewpoint of guidance and control, realizing formation flying mission usually requires tight maintenance and control of the relative distances, speeds and orientations between the member satellites. This paper studies a practical architecture for formation flight missions focusing mainly on guidance and control, and describes a new guidance algorithm for changing and keeping the relative positions and speeds of the satellites in formation. The resulting algorithm is suitable for onboard processing and gives the optimum impulsive trajectory for satellites flying closely around a certain reference orbit, that can be elliptic, parabolic or hyperbolic. Based on this guidance algorithm, this study introduces an information management methodology between the member spacecrafts which is suitable for a large formation flight architecture. Routing and multicast communication based on the wireless local area network technology are introduced. Some mathematical analyses and computer simulations will be shown in the presentation to reveal the feasibility of the proposed formation flight architecture, especially when a very large number of satellites join the formation.

Artificial neural network modeling and optimization of ultrahigh pressure extraction of green tea polyphenols.

PubMed

Xi, Jun; Xue, Yujing; Xu, Yinxiang; Shen, Yuhong

2013-11-01

In this study, the ultrahigh pressure extraction of green tea polyphenols was modeled and optimized by a three-layer artificial neural network. A feed-forward neural network trained with an error back-propagation algorithm was used to evaluate the effects of pressure, liquid/solid ratio and ethanol concentration on the total phenolic content of green tea extracts. The neural network coupled with genetic algorithms was also used to optimize the conditions needed to obtain the highest yield of tea polyphenols. The obtained optimal architecture of artificial neural network model involved a feed-forward neural network with three input neurons, one hidden layer with eight neurons and one output layer including single neuron. The trained network gave the minimum value in the MSE of 0.03 and the maximum value in the R(2) of 0.9571, which implied a good agreement between the predicted value and the actual value, and confirmed a good generalization of the network. Based on the combination of neural network and genetic algorithms, the optimum extraction conditions for the highest yield of green tea polyphenols were determined as follows: 498.8 MPa for pressure, 20.8 mL/g for liquid/solid ratio and 53.6% for ethanol concentration. The total phenolic content of the actual measurement under the optimum predicated extraction conditions was 582.4 ± 0.63 mg/g DW, which was well matched with the predicted value (597.2mg/g DW). This suggests that the artificial neural network model described in this work is an efficient quantitative tool to predict the extraction efficiency of green tea polyphenols. Crown Copyright © 2013. Published by Elsevier Ltd. All rights reserved.

USC orthogonal multiprocessor for image processing with neural networks

NASA Astrophysics Data System (ADS)

Hwang, Kai; Panda, Dhabaleswar K.; Haddadi, Navid

1990-07-01

This paper presents the architectural features and imaging applications of the Orthogonal MultiProcessor (OMP) system, which is under construction at the University of Southern California with research funding from NSF and assistance from several industrial partners. The prototype OMP is being built with 16 Intel i860 RISC microprocessors and 256 parallel memory modules using custom-designed spanning buses, which are 2-D interleaved and orthogonally accessed without conflicts. The 16-processor OMP prototype is targeted to achieve 430 MIPS and 600 Mflops, which have been verified by simulation experiments based on the design parameters used. The prototype OMP machine will be initially applied for image processing, computer vision, and neural network simulation applications. We summarize important vision and imaging algorithms that can be restructured with neural network models. These algorithms can efficiently run on the OMP hardware with linear speedup. The ultimate goal is to develop a high-performance Visual Computer (Viscom) for integrated low- and high-level image processing and vision tasks.

Self-Adaptive Prediction of Cloud Resource Demands Using Ensemble Model and Subtractive-Fuzzy Clustering Based Fuzzy Neural Network

PubMed Central

Chen, Zhijia; Zhu, Yuanchang; Di, Yanqiang; Feng, Shaochong

2015-01-01

In IaaS (infrastructure as a service) cloud environment, users are provisioned with virtual machines (VMs). To allocate resources for users dynamically and effectively, accurate resource demands predicting is essential. For this purpose, this paper proposes a self-adaptive prediction method using ensemble model and subtractive-fuzzy clustering based fuzzy neural network (ESFCFNN). We analyze the characters of user preferences and demands. Then the architecture of the prediction model is constructed. We adopt some base predictors to compose the ensemble model. Then the structure and learning algorithm of fuzzy neural network is researched. To obtain the number of fuzzy rules and the initial value of the premise and consequent parameters, this paper proposes the fuzzy c-means combined with subtractive clustering algorithm, that is, the subtractive-fuzzy clustering. Finally, we adopt different criteria to evaluate the proposed method. The experiment results show that the method is accurate and effective in predicting the resource demands. PMID:25691896

Energy management and multi-layer control of networked microgrids

NASA Astrophysics Data System (ADS)

Zamora, Ramon

Networked microgrids is a group of neighboring microgrids that has ability to interchange power when required in order to increase reliability and resiliency. Networked microgrid can operate in different possible configurations including: islanded microgrid, a grid-connected microgrid without a tie-line converter, a grid-connected microgrid with a tie-line converter, and networked microgrids. These possible configurations and specific characteristics of renewable energy offer challenges in designing control and management algorithms for voltage, frequency and power in all possible operating scenarios. In this work, control algorithm is designed based on large-signal model that enables microgrid to operate in wide range of operating points. A combination between PI controller and feed-forward measured system responses will compensate for the changes in operating points. The control architecture developed in this work has multi-layers and the outer layer is slower than the inner layer in time response. The main responsibility of the designed controls are to regulate voltage magnitude and frequency, as well as output power of the DG(s). These local controls also integrate with a microgrid level energy management system or microgrid central controller (MGCC) for power and energy balance for. the entire microgrid in islanded, grid-connected, or networked microgid mode. The MGCC is responsible to coordinate the lower level controls to have reliable and resilient operation. In case of communication network failure, the decentralized energy management will operate locally and will activate droop control. Simulation results indicate the superiority of designed control algorithms compared to existing ones.

Clustering and Flow Conservation Monitoring Tool for Software Defined Networks

PubMed Central

Puente Fernández, Jesús Antonio

2018-01-01

Prediction systems present some challenges on two fronts: the relation between video quality and observed session features and on the other hand, dynamics changes on the video quality. Software Defined Networks (SDN) is a new concept of network architecture that provides the separation of control plane (controller) and data plane (switches) in network devices. Due to the existence of the southbound interface, it is possible to deploy monitoring tools to obtain the network status and retrieve a statistics collection. Therefore, achieving the most accurate statistics depends on a strategy of monitoring and information requests of network devices. In this paper, we propose an enhanced algorithm for requesting statistics to measure the traffic flow in SDN networks. Such an algorithm is based on grouping network switches in clusters focusing on their number of ports to apply different monitoring techniques. Such grouping occurs by avoiding monitoring queries in network switches with common characteristics and then, by omitting redundant information. In this way, the present proposal decreases the number of monitoring queries to switches, improving the network traffic and preventing the switching overload. We have tested our optimization in a video streaming simulation using different types of videos. The experiments and comparison with traditional monitoring techniques demonstrate the feasibility of our proposal maintaining similar values decreasing the number of queries to the switches. PMID:29614049

Managed traffic evacuation using distributed sensor processing

NASA Astrophysics Data System (ADS)

Ramuhalli, Pradeep; Biswas, Subir

2005-05-01

This paper presents an integrated sensor network and distributed event processing architecture for managed in-building traffic evacuation during natural and human-caused disasters, including earthquakes, fire and biological/chemical terrorist attacks. The proposed wireless sensor network protocols and distributed event processing mechanisms offer a new distributed paradigm for improving reliability in building evacuation and disaster management. The networking component of the system is constructed using distributed wireless sensors for measuring environmental parameters such as temperature, humidity, and detecting unusual events such as smoke, structural failures, vibration, biological/chemical or nuclear agents. Distributed event processing algorithms will be executed by these sensor nodes to detect the propagation pattern of the disaster and to measure the concentration and activity of human traffic in different parts of the building. Based on this information, dynamic evacuation decisions are taken for maximizing the evacuation speed and minimizing unwanted incidents such as human exposure to harmful agents and stampedes near exits. A set of audio-visual indicators and actuators are used for aiding the automated evacuation process. In this paper we develop integrated protocols, algorithms and their simulation models for the proposed sensor networking and the distributed event processing framework. Also, efficient harnessing of the individually low, but collectively massive, processing abilities of the sensor nodes is a powerful concept behind our proposed distributed event processing algorithms. Results obtained through simulation in this paper are used for a detailed characterization of the proposed evacuation management system and its associated algorithmic components.

Applications and development of communication models for the touchstone GAMMA and DELTA prototypes

NASA Technical Reports Server (NTRS)

Seidel, Steven R.

1993-01-01

The goal of this project was to develop models of the interconnection networks of the Intel iPSC/860 and DELTA multicomputers to guide the design of efficient algorithms for interprocessor communication in problems that commonly occur in CFD codes and other applications. Interprocessor communication costs of codes for message-passing architectures such as the iPSC/860 and DELTA significantly affect the level of performance that can be obtained from those machines. This project addressed several specific problems in the achievement of efficient communication on the Intel iPSC/860 hypercube and DELTA mesh. In particular, an efficient global processor synchronization algorithm was developed for the iPSC/860 and numerous broadcast algorithms were designed for the DELTA.

A review and analysis of neural networks for classification of remotely sensed multispectral imagery

NASA Technical Reports Server (NTRS)

Paola, Justin D.; Schowengerdt, Robert A.

1993-01-01

A literature survey and analysis of the use of neural networks for the classification of remotely sensed multispectral imagery is presented. As part of a brief mathematical review, the backpropagation algorithm, which is the most common method of training multi-layer networks, is discussed with an emphasis on its application to pattern recognition. The analysis is divided into five aspects of neural network classification: (1) input data preprocessing, structure, and encoding; (2) output encoding and extraction of classes; (3) network architecture, (4) training algorithms; and (5) comparisons to conventional classifiers. The advantages of the neural network method over traditional classifiers are its non-parametric nature, arbitrary decision boundary capabilities, easy adaptation to different types of data and input structures, fuzzy output values that can enhance classification, and good generalization for use with multiple images. The disadvantages of the method are slow training time, inconsistent results due to random initial weights, and the requirement of obscure initialization values (e.g., learning rate and hidden layer size). Possible techniques for ameliorating these problems are discussed. It is concluded that, although the neural network method has several unique capabilities, it will become a useful tool in remote sensing only if it is made faster, more predictable, and easier to use.

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.

influx_s: increasing numerical stability and precision for metabolic flux analysis in isotope labelling experiments.

PubMed

Sokol, Serguei; Millard, Pierre; Portais, Jean-Charles

2012-03-01

The problem of stationary metabolic flux analysis based on isotope labelling experiments first appeared in the early 1950s and was basically solved in early 2000s. Several algorithms and software packages are available for this problem. However, the generic stochastic algorithms (simulated annealing or evolution algorithms) currently used in these software require a lot of time to achieve acceptable precision. For deterministic algorithms, a common drawback is the lack of convergence stability for ill-conditioned systems or when started from a random point. In this article, we present a new deterministic algorithm with significantly increased numerical stability and accuracy of flux estimation compared with commonly used algorithms. It requires relatively short CPU time (from several seconds to several minutes with a standard PC architecture) to estimate fluxes in the central carbon metabolism network of Escherichia coli. The software package influx_s implementing this algorithm is distributed under an OpenSource licence at http://metasys.insa-toulouse.fr/software/influx/. Supplementary data are available at Bioinformatics online.

Cascaded VLSI Chips Help Neural Network To Learn

NASA Technical Reports Server (NTRS)

Duong, Tuan A.; Daud, Taher; Thakoor, Anilkumar P.

1993-01-01

Cascading provides 12-bit resolution needed for learning. Using conventional silicon chip fabrication technology of VLSI, fully connected architecture consisting of 32 wide-range, variable gain, sigmoidal neurons along one diagonal and 7-bit resolution, electrically programmable, synaptic 32 x 31 weight matrix implemented on neuron-synapse chip. To increase weight nominally from 7 to 13 bits, synapses on chip individually cascaded with respective synapses on another 32 x 32 matrix chip with 7-bit resolution synapses only (without neurons). Cascade correlation algorithm varies number of layers effectively connected into network; adds hidden layers one at a time during learning process in such way as to optimize overall number of neurons and complexity and configuration of network.

Neural networks for tracking of unknown SISO discrete-time nonlinear dynamic systems.

PubMed

Aftab, Muhammad Saleheen; Shafiq, Muhammad

2015-11-01

This article presents a Lyapunov function based neural network tracking (LNT) strategy for single-input, single-output (SISO) discrete-time nonlinear dynamic systems. The proposed LNT architecture is composed of two feedforward neural networks operating as controller and estimator. A Lyapunov function based back propagation learning algorithm is used for online adjustment of the controller and estimator parameters. The controller and estimator error convergence and closed-loop system stability analysis is performed by Lyapunov stability theory. Moreover, two simulation examples and one real-time experiment are investigated as case studies. The achieved results successfully validate the controller performance. Copyright © 2015 ISA. Published by Elsevier Ltd. All rights reserved.

Scaling deep learning workloads: NVIDIA DGX-1/Pascal and Intel Knights Landing

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

Gawande, Nitin A.; Landwehr, Joshua B.; Daily, Jeffrey A.

Deep Learning (DL) algorithms have become ubiquitous in data analytics. As a result, major computing vendors --- including NVIDIA, Intel, AMD, and IBM --- have architectural road-maps influenced by DL workloads. Furthermore, several vendors have recently advertised new computing products as accelerating large DL workloads. Unfortunately, it is difficult for data scientists to quantify the potential of these different products. This paper provides a performance and power analysis of important DL workloads on two major parallel architectures: NVIDIA DGX-1 (eight Pascal P100 GPUs interconnected with NVLink) and Intel Knights Landing (KNL) CPUs interconnected with Intel Omni-Path or Cray Aries. Ourmore » evaluation consists of a cross section of convolutional neural net workloads: CifarNet, AlexNet, GoogLeNet, and ResNet50 topologies using the Cifar10 and ImageNet datasets. The workloads are vendor-optimized for each architecture. Our analysis indicates that although GPUs provide the highest overall performance, the gap can close for some convolutional networks; and the KNL can be competitive in performance/watt. We find that NVLink facilitates scaling efficiency on GPUs. However, its importance is heavily dependent on neural network architecture. Furthermore, for weak-scaling --- sometimes encouraged by restricted GPU memory --- NVLink is less important.« less

ICC '86; Proceedings of the International Conference on Communications, Toronto, Canada, June 22-25, 1986, Conference Record. Volumes 1, 2, & 3

NASA Astrophysics Data System (ADS)

Papers are presented on ISDN, mobile radio systems and techniques for digital connectivity, centralized and distributed algorithms in computer networks, communications networks, quality assurance and impact on cost, adaptive filters in communications, the spread spectrum, signal processing, video communication techniques, and digital satellite services. Topics discussed include performance evaluation issues for integrated protocols, packet network operations, the computer network theory and multiple-access, microwave single sideband systems, switching architectures, fiber optic systems, wireless local communications, modulation, coding, and synchronization, remote switching, software quality, transmission, and expert systems in network operations. Consideration is given to wide area networks, image and speech processing, office communications application protocols, multimedia systems, customer-controlled network operations, digital radio systems, channel modeling and signal processing in digital communications, earth station/on-board modems, computer communications system performance evaluation, source encoding, compression, and quantization, and adaptive communications systems.

Detection and Monitoring of Improvised Explosive Device Education Networks through the World Wide Web

DTIC Science & Technology

2009-06-01

search engines are not up to this task, as they have been optimized to catalog information quickly and efficiently for user ease of access while promoting retail commerce at the same time. This thesis presents a performance analysis of a new search engine algorithm designed to help find IED education networks using the Nutch open-source search engine architecture. It reveals which web pages are more important via references from other web pages regardless of domain. In addition, this thesis discusses potential evaluation and monitoring techniques to be used in conjunction

Pubface: Celebrity face identification based on deep learning

NASA Astrophysics Data System (ADS)

Ouanan, H.; Ouanan, M.; Aksasse, B.

2018-05-01

In this paper, we describe a new real time application called PubFace, which allows to recognize celebrities in public spaces by employs a new pose invariant face recognition deep neural network algorithm with an extremely low error rate. To build this application, we make the following contributions: firstly, we build a novel dataset with over five million faces labelled. Secondly, we fine tuning the deep convolutional neural network (CNN) VGG-16 architecture on our new dataset that we have built. Finally, we deploy this model on the Raspberry Pi 3 model B using the OpenCv dnn module (OpenCV 3.3).

An Energy-Efficient and Scalable Deep Learning/Inference Processor With Tetra-Parallel MIMD Architecture for Big Data Applications.

PubMed

Park, Seong-Wook; Park, Junyoung; Bong, Kyeongryeol; Shin, Dongjoo; Lee, Jinmook; Choi, Sungpill; Yoo, Hoi-Jun

2015-12-01

Deep Learning algorithm is widely used for various pattern recognition applications such as text recognition, object recognition and action recognition because of its best-in-class recognition accuracy compared to hand-crafted algorithm and shallow learning based algorithms. Long learning time caused by its complex structure, however, limits its usage only in high-cost servers or many-core GPU platforms so far. On the other hand, the demand on customized pattern recognition within personal devices will grow gradually as more deep learning applications will be developed. This paper presents a SoC implementation to enable deep learning applications to run with low cost platforms such as mobile or portable devices. Different from conventional works which have adopted massively-parallel architecture, this work adopts task-flexible architecture and exploits multiple parallelism to cover complex functions of convolutional deep belief network which is one of popular deep learning/inference algorithms. In this paper, we implement the most energy-efficient deep learning and inference processor for wearable system. The implemented 2.5 mm × 4.0 mm deep learning/inference processor is fabricated using 65 nm 8-metal CMOS technology for a battery-powered platform with real-time deep inference and deep learning operation. It consumes 185 mW average power, and 213.1 mW peak power at 200 MHz operating frequency and 1.2 V supply voltage. It achieves 411.3 GOPS peak performance and 1.93 TOPS/W energy efficiency, which is 2.07× higher than the state-of-the-art.

Flexible distributed architecture for semiconductor process control and experimentation

NASA Astrophysics Data System (ADS)

Gower, Aaron E.; Boning, Duane S.; McIlrath, Michael B.

1997-01-01

Semiconductor fabrication requires an increasingly expensive and integrated set of tightly controlled processes, driving the need for a fabrication facility with fully computerized, networked processing equipment. We describe an integrated, open system architecture enabling distributed experimentation and process control for plasma etching. The system was developed at MIT's Microsystems Technology Laboratories and employs in-situ CCD interferometry based analysis in the sensor-feedback control of an Applied Materials Precision 5000 Plasma Etcher (AME5000). Our system supports accelerated, advanced research involving feedback control algorithms, and includes a distributed interface that utilizes the internet to make these fabrication capabilities available to remote users. The system architecture is both distributed and modular: specific implementation of any one task does not restrict the implementation of another. The low level architectural components include a host controller that communicates with the AME5000 equipment via SECS-II, and a host controller for the acquisition and analysis of the CCD sensor images. A cell controller (CC) manages communications between these equipment and sensor controllers. The CC is also responsible for process control decisions; algorithmic controllers may be integrated locally or via remote communications. Finally, a system server images connections from internet/intranet (web) based clients and uses a direct link with the CC to access the system. Each component communicates via a predefined set of TCP/IP socket based messages. This flexible architecture makes integration easier and more robust, and enables separate software components to run on the same or different computers independent of hardware or software platform.

A DNA-Inspired Encryption Methodology for Secure, Mobile Ad Hoc Networks

NASA Technical Reports Server (NTRS)

Shaw, Harry

2012-01-01

Users are pushing for greater physical mobility with their network and Internet access. Mobile ad hoc networks (MANET) can provide an efficient mobile network architecture, but security is a key concern. A figure summarizes differences in the state of network security for MANET and fixed networks. MANETs require the ability to distinguish trusted peers, and tolerate the ingress/egress of nodes on an unscheduled basis. Because the networks by their very nature are mobile and self-organizing, use of a Public Key Infra structure (PKI), X.509 certificates, RSA, and nonce ex changes becomes problematic if the ideal of MANET is to be achieved. Molecular biology models such as DNA evolution can provide a basis for a proprietary security architecture that achieves high degrees of diffusion and confusion, and resistance to cryptanalysis. A proprietary encryption mechanism was developed that uses the principles of DNA replication and steganography (hidden word cryptography) for confidentiality and authentication. The foundation of the approach includes organization of coded words and messages using base pairs organized into genes, an expandable genome consisting of DNA-based chromosome keys, and a DNA-based message encoding, replication, and evolution and fitness. In evolutionary computing, a fitness algorithm determines whether candidate solutions, in this case encrypted messages, are sufficiently encrypted to be transmitted. The technology provides a mechanism for confidential electronic traffic over a MANET without a PKI for authenticating users.

Autonomic Intelligent Cyber Sensor to Support Industrial Control Network Awareness

DOE PAGES

Vollmer, Todd; Manic, Milos; Linda, Ondrej

2013-06-01

The proliferation of digital devices in a networked industrial ecosystem, along with an exponential growth in complexity and scope, has resulted in elevated security concerns and management complexity issues. This paper describes a novel architecture utilizing concepts of Autonomic computing and a SOAP based IF-MAP external communication layer to create a network security sensor. This approach simplifies integration of legacy software and supports a secure, scalable, self-managed framework. The contribution of this paper is two-fold: 1) A flexible two level communication layer based on Autonomic computing and Service Oriented Architecture is detailed and 2) Three complementary modules that dynamically reconfiguremore » in response to a changing environment are presented. One module utilizes clustering and fuzzy logic to monitor traffic for abnormal behavior. Another module passively monitors network traffic and deploys deceptive virtual network hosts. These components of the sensor system were implemented in C++ and PERL and utilize a common internal D-Bus communication mechanism. A proof of concept prototype was deployed on a mixed-use test network showing the possible real world applicability. In testing, 45 of the 46 network attached devices were recognized and 10 of the 12 emulated devices were created with specific Operating System and port configurations. Additionally the anomaly detection algorithm achieved a 99.9% recognition rate. All output from the modules were correctly distributed using the common communication structure.« less

Factoring symmetric indefinite matrices on high-performance architectures

NASA Technical Reports Server (NTRS)

Jones, Mark T.; Patrick, Merrell L.

1990-01-01

The Bunch-Kaufman algorithm is the method of choice for factoring symmetric indefinite matrices in many applications. However, the Bunch-Kaufman algorithm does not take advantage of high-performance architectures such as the Cray Y-MP. Three new algorithms, based on Bunch-Kaufman factorization, that take advantage of such architectures are described. Results from an implementation of the third algorithm are presented.

An Architecture for Enabling Migration of Tactical Networks to Future Flexible Ad Hoc WBWF

DTIC Science & Technology

2010-09-01

Requirements Several multiple access schemes TDMA OFDMA SC-OFDMA, FH- CDMA , DS - CDMA , hybrid access schemes, transitions between them Dynamic...parameters algorithms depend on the multiple access scheme If DS - CDMA : handling of macro-diversity (linked to cooperative routing) TDMA and/of OFDMA...Transport format Ciphering @MAC/RLC level : SCM Physical layer (PHY) : signal processing (mod, FEC, etc) CDMA : macro-diversity CDMA , OFDMA

Accelerating artificial intelligence with reconfigurable computing

NASA Astrophysics Data System (ADS)

Cieszewski, Radoslaw

Reconfigurable computing is emerging as an important area of research in computer architectures and software systems. Many algorithms can be greatly accelerated by placing the computationally intense portions of an algorithm into reconfigurable hardware. Reconfigurable computing combines many benefits of both software and ASIC implementations. Like software, the mapped circuit is flexible, and can be changed over the lifetime of the system. Similar to an ASIC, reconfigurable systems provide a method to map circuits into hardware. Reconfigurable systems therefore have the potential to achieve far greater performance than software as a result of bypassing the fetch-decode-execute operations of traditional processors, and possibly exploiting a greater level of parallelism. Such a field, where there is many different algorithms which can be accelerated, is an artificial intelligence. This paper presents example hardware implementations of Artificial Neural Networks, Genetic Algorithms and Expert Systems.

A generalized locomotion CPG architecture based on oscillatory building blocks.

PubMed

Yang, Zhijun; França, Felipe M G

2003-07-01

Neural oscillation is one of the most extensively investigated topics of artificial neural networks. Scientific approaches to the functionalities of both natural and artificial intelligences are strongly related to mechanisms underlying oscillatory activities. This paper concerns itself with the assumption of the existence of central pattern generators (CPGs), which are the plausible neural architectures with oscillatory capabilities, and presents a discrete and generalized approach to the functionality of locomotor CPGs of legged animals. Based on scheduling by multiple edge reversal (SMER), a primitive and deterministic distributed algorithm, it is shown how oscillatory building block (OBB) modules can be created and, hence, how OBB-based networks can be formulated as asymmetric Hopfield-like neural networks for the generation of complex coordinated rhythmic patterns observed among pairs of biological motor neurons working during different gait patterns. It is also shown that the resulting Hopfield-like network possesses the property of reproducing the whole spectrum of different gaits intrinsic to the target locomotor CPGs. Although the new approach is not restricted to the understanding of the neurolocomotor system of any particular animal, hexapodal and quadrupedal gait patterns are chosen as illustrations given the wide interest expressed by the ongoing research in the area.

Applications of wireless sensor networks in marine environment monitoring: a survey.

PubMed

Xu, Guobao; Shen, Weiming; Wang, Xianbin

2014-09-11

With the rapid development of society and the economy, an increasing number of human activities have gradually destroyed the marine environment. Marine environment monitoring is a vital problem and has increasingly attracted a great deal of research and development attention. During the past decade, various marine environment monitoring systems have been developed. The traditional marine environment monitoring system using an oceanographic research vessel is expensive and time-consuming and has a low resolution both in time and space. Wireless Sensor Networks (WSNs) have recently been considered as potentially promising alternatives for monitoring marine environments since they have a number of advantages such as unmanned operation, easy deployment, real-time monitoring, and relatively low cost. This paper provides a comprehensive review of the state-of-the-art technologies in the field of marine environment monitoring using wireless sensor networks. It first describes application areas, a common architecture of WSN-based oceanographic monitoring systems, a general architecture of an oceanographic sensor node, sensing parameters and sensors, and wireless communication technologies. Then, it presents a detailed review of some related projects, systems, techniques, approaches and algorithms. It also discusses challenges and opportunities in the research, development, and deployment of wireless sensor networks for marine environment monitoring.

Low-complexity nonlinear adaptive filter based on a pipelined bilinear recurrent neural network.

PubMed

Zhao, Haiquan; Zeng, Xiangping; He, Zhengyou

2011-09-01

To reduce the computational complexity of the bilinear recurrent neural network (BLRNN), a novel low-complexity nonlinear adaptive filter with a pipelined bilinear recurrent neural network (PBLRNN) is presented in this paper. The PBLRNN, inheriting the modular architectures of the pipelined RNN proposed by Haykin and Li, comprises a number of BLRNN modules that are cascaded in a chained form. Each module is implemented by a small-scale BLRNN with internal dynamics. Since those modules of the PBLRNN can be performed simultaneously in a pipelined parallelism fashion, it would result in a significant improvement of computational efficiency. Moreover, due to nesting module, the performance of the PBLRNN can be further improved. To suit for the modular architectures, a modified adaptive amplitude real-time recurrent learning algorithm is derived on the gradient descent approach. Extensive simulations are carried out to evaluate the performance of the PBLRNN on nonlinear system identification, nonlinear channel equalization, and chaotic time series prediction. Experimental results show that the PBLRNN provides considerably better performance compared to the single BLRNN and RNN models.

Efficient Aho-Corasick String Matching on Emerging Multicore Architectures

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

Tumeo, Antonino; Villa, Oreste; Secchi, Simone

String matching algorithms are critical to several scientific fields. Beside text processing and databases, emerging applications such as DNA protein sequence analysis, data mining, information security software, antivirus, ma- chine learning, all exploit string matching algorithms [3]. All these applica- tions usually process large quantity of textual data, require high performance and/or predictable execution times. Among all the string matching algorithms, one of the most studied, especially for text processing and security applica- tions, is the Aho-Corasick algorithm. 1 2 Book title goes here Aho-Corasick is an exact, multi-pattern string matching algorithm which performs the search in a time linearlymore » proportional to the length of the input text independently from pattern set size. However, depending on the imple- mentation, when the number of patterns increase, the memory occupation may raise drastically. In turn, this can lead to significant variability in the performance, due to the memory access times and the caching effects. This is a significant concern for many mission critical applications and modern high performance architectures. For example, security applications such as Network Intrusion Detection Systems (NIDS), must be able to scan network traffic against very large dictionaries in real time. Modern Ethernet links reach up to 10 Gbps, and malicious threats are already well over 1 million, and expo- nentially growing [28]. When performing the search, a NIDS should not slow down the network, or let network packets pass unchecked. Nevertheless, on the current state-of-the-art cache based processors, there may be a large per- formance variability when dealing with big dictionaries and inputs that have different frequencies of matching patterns. In particular, when few patterns are matched and they are all in the cache, the procedure is fast. Instead, when they are not in the cache, often because many patterns are matched and the caches are continuously thrashed, they should be retrieved from the system memory and the procedure is slowed down by the increased latency. Efficient implementations of string matching algorithms have been the fo- cus of several works, targeting Field Programmable Gate Arrays [4, 25, 15, 5], highly multi-threaded solutions like the Cray XMT [34], multicore proces- sors [19] or heterogeneous processors like the Cell Broadband Engine [35, 22]. Recently, several researchers have also started to investigate the use Graphic Processing Units (GPUs) for string matching algorithms in security applica- tions [20, 10, 32, 33]. Most of these approaches mainly focus on reaching high peak performance, or try to optimize the memory occupation, rather than looking at performance stability. However, hardware solutions supports only small dictionary sizes due to lack of memory and are difficult to customize, while platforms such as the Cell/B.E. are very complex to program.« less

Planning Multitechnology Access Networks with Performance Constraints

NASA Astrophysics Data System (ADS)

Chamberland, Steven

Considering the number of access network technologies and the investment needed for the “last mile” of a solution, in today’s highly competitive markets, planning tools are crucial for the service providers to optimize the network costs and accelerate the planning process. In this paper, we propose to tackle the problem of planning access networks composed of four technologies/architectures: the digital subscriber line (xDSL) technologies deployed directly from the central office (CO), the fiber-to-the-node (FTTN), the fiber-to-the-micro-node (FTTn) and the fiber-to-the-premises (FTTP). A mathematical programming model is proposed for this planning problem that is solved using a commercial implementation of the branch-and-bound algorithm. Next, a detailed access network planning example is presented followed by a systematic set of experiments designed to assess the performance of the proposed approach.

A Faster Parallel Algorithm and Efficient Multithreaded Implementations for Evaluating Betweenness Centrality on Massive Datasets

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

Madduri, Kamesh; Ediger, David; Jiang, Karl

2009-02-15

We present a new lock-free parallel algorithm for computing betweenness centralityof massive small-world networks. With minor changes to the data structures, ouralgorithm also achieves better spatial cache locality compared to previous approaches. Betweenness centrality is a key algorithm kernel in HPCS SSCA#2, a benchmark extensively used to evaluate the performance of emerging high-performance computing architectures for graph-theoretic computations. We design optimized implementations of betweenness centrality and the SSCA#2 benchmark for two hardware multithreaded systems: a Cray XMT system with the Threadstorm processor, and a single-socket Sun multicore server with the UltraSPARC T2 processor. For a small-world network of 134 millionmore » vertices and 1.073 billion edges, the 16-processor XMT system and the 8-core Sun Fire T5120 server achieve TEPS scores (an algorithmic performance count for the SSCA#2 benchmark) of 160 million and 90 million respectively, which corresponds to more than a 2X performance improvement over the previous parallel implementations. To better characterize the performance of these multithreaded systems, we correlate the SSCA#2 performance results with data from the memory-intensive STREAM and RandomAccess benchmarks. Finally, we demonstrate the applicability of our implementation to analyze massive real-world datasets by computing approximate betweenness centrality for a large-scale IMDb movie-actor network.« less

Robust Bioinformatics Recognition with VLSI Biochip Microsystem

NASA Technical Reports Server (NTRS)

Lue, Jaw-Chyng L.; Fang, Wai-Chi

2006-01-01

A microsystem architecture for real-time, on-site, robust bioinformatic patterns recognition and analysis has been proposed. This system is compatible with on-chip DNA analysis means such as polymerase chain reaction (PCR)amplification. A corresponding novel artificial neural network (ANN) learning algorithm using new sigmoid-logarithmic transfer function based on error backpropagation (EBP) algorithm is invented. Our results show the trained new ANN can recognize low fluorescence patterns better than the conventional sigmoidal ANN does. A differential logarithmic imaging chip is designed for calculating logarithm of relative intensities of fluorescence signals. The single-rail logarithmic circuit and a prototype ANN chip are designed, fabricated and characterized.

Strategy for Developing Expert-System-Based Internet Protocols (TCP/IP)

NASA Technical Reports Server (NTRS)

Ivancic, William D.

1997-01-01

The Satellite Networks and Architectures Branch of NASA's Lewis Research is addressing the issue of seamless interoperability of satellite networks with terrestrial networks. One of the major issues is improving reliable transmission protocols such as TCP over long latency and error-prone links. Many tuning parameters are available to enhance the performance of TCP including segment size, timers and window sizes. There are also numerous congestion avoidance algorithms such as slow start, selective retransmission and selective acknowledgment that are utilized to improve performance. This paper provides a strategy to characterize the performance of TCP relative to various parameter settings in a variety of network environments (i.e. LAN, WAN, wireless, satellite, and IP over ATM). This information can then be utilized to develop expert-system-based Internet protocols.

Cascaded Segmentation-Detection Networks for Word-Level Text Spotting.

PubMed

Qin, Siyang; Manduchi, Roberto

2017-11-01

We introduce an algorithm for word-level text spotting that is able to accurately and reliably determine the bounding regions of individual words of text "in the wild". Our system is formed by the cascade of two convolutional neural networks. The first network is fully convolutional and is in charge of detecting areas containing text. This results in a very reliable but possibly inaccurate segmentation of the input image. The second network (inspired by the popular YOLO architecture) analyzes each segment produced in the first stage, and predicts oriented rectangular regions containing individual words. No post-processing (e.g. text line grouping) is necessary. With execution time of 450 ms for a 1000 × 560 image on a Titan X GPU, our system achieves good performance on the ICDAR 2013, 2015 benchmarks [2], [1].

Reverse engineering a gene network using an asynchronous parallel evolution strategy

PubMed Central

2010-01-01

Background The use of reverse engineering methods to infer gene regulatory networks by fitting mathematical models to gene expression data is becoming increasingly popular and successful. However, increasing model complexity means that more powerful global optimisation techniques are required for model fitting. The parallel Lam Simulated Annealing (pLSA) algorithm has been used in such approaches, but recent research has shown that island Evolutionary Strategies can produce faster, more reliable results. However, no parallel island Evolutionary Strategy (piES) has yet been demonstrated to be effective for this task. Results Here, we present synchronous and asynchronous versions of the piES algorithm, and apply them to a real reverse engineering problem: inferring parameters in the gap gene network. We find that the asynchronous piES exhibits very little communication overhead, and shows significant speed-up for up to 50 nodes: the piES running on 50 nodes is nearly 10 times faster than the best serial algorithm. We compare the asynchronous piES to pLSA on the same test problem, measuring the time required to reach particular levels of residual error, and show that it shows much faster convergence than pLSA across all optimisation conditions tested. Conclusions Our results demonstrate that the piES is consistently faster and more reliable than the pLSA algorithm on this problem, and scales better with increasing numbers of nodes. In addition, the piES is especially well suited to further improvements and adaptations: Firstly, the algorithm's fast initial descent speed and high reliability make it a good candidate for being used as part of a global/local search hybrid algorithm. Secondly, it has the potential to be used as part of a hierarchical evolutionary algorithm, which takes advantage of modern multi-core computing architectures. PMID:20196855

Research and application of ARP protocol vulnerability attack and defense technology based on trusted network

NASA Astrophysics Data System (ADS)

Xi, Huixing

2017-03-01

With the continuous development of network technology and the rapid spread of the Internet, computer networks have been around the world every corner. However, the network attacks frequently occur. The ARP protocol vulnerability is one of the most common vulnerabilities in the TCP / IP four-layer architecture. The network protocol vulnerabilities can lead to the intrusion and attack of the information system, and disable or disable the normal defense function of the system [1]. At present, ARP spoofing Trojans spread widely in the LAN, the network security to run a huge hidden danger, is the primary threat to LAN security. In this paper, the author summarizes the research status and the key technologies involved in ARP protocol, analyzes the formation mechanism of ARP protocol vulnerability, and analyzes the feasibility of the attack technique. Based on the summary of the common defensive methods, the advantages and disadvantages of each defense method. At the same time, the current defense method is improved, and the advantage of the improved defense algorithm is given. At the end of this paper, the appropriate test method is selected and the test environment is set up. Experiment and test are carried out for each proposed improved defense algorithm.

Fast decision algorithms in low-power embedded processors for quality-of-service based connectivity of mobile sensors in heterogeneous wireless sensor networks.

PubMed

Jaraíz-Simón, María D; Gómez-Pulido, Juan A; Vega-Rodríguez, Miguel A; Sánchez-Pérez, Juan M

2012-01-01

When a mobile wireless sensor is moving along heterogeneous wireless sensor networks, it can be under the coverage of more than one network many times. In these situations, the Vertical Handoff process can happen, where the mobile sensor decides to change its connection from a network to the best network among the available ones according to their quality of service characteristics. A fitness function is used for the handoff decision, being desirable to minimize it. This is an optimization problem which consists of the adjustment of a set of weights for the quality of service. Solving this problem efficiently is relevant to heterogeneous wireless sensor networks in many advanced applications. Numerous works can be found in the literature dealing with the vertical handoff decision, although they all suffer from the same shortfall: a non-comparable efficiency. Therefore, the aim of this work is twofold: first, to develop a fast decision algorithm that explores the entire space of possible combinations of weights, searching that one that minimizes the fitness function; and second, to design and implement a system on chip architecture based on reconfigurable hardware and embedded processors to achieve several goals necessary for competitive mobile terminals: good performance, low power consumption, low economic cost, and small area integration.

A complex network-based importance measure for mechatronics systems

NASA Astrophysics Data System (ADS)

Wang, Yanhui; Bi, Lifeng; Lin, Shuai; Li, Man; Shi, Hao

2017-01-01

In view of the negative impact of functional dependency, this paper attempts to provide an alternative importance measure called Improved-PageRank (IPR) for measuring the importance of components in mechatronics systems. IPR is a meaningful extension of the centrality measures in complex network, which considers usage reliability of components and functional dependency between components to increase importance measures usefulness. Our work makes two important contributions. First, this paper integrates the literature of mechatronic architecture and complex networks theory to define component network. Second, based on the notion of component network, a meaningful IPR is brought into the identifying of important components. In addition, the IPR component importance measures, and an algorithm to perform stochastic ordering of components due to the time-varying nature of usage reliability of components and functional dependency between components, are illustrated with a component network of bogie system that consists of 27 components.

Transmission Scheduling and Routing Algorithms for Delay Tolerant Networks

NASA Technical Reports Server (NTRS)

Dudukovich, Rachel; Raible, Daniel E.

2016-01-01

The challenges of data processing, transmission scheduling and routing within a space network present a multi-criteria optimization problem. Long delays, intermittent connectivity, asymmetric data rates and potentially high error rates make traditional networking approaches unsuitable. The delay tolerant networking architecture and protocols attempt to mitigate many of these issues, yet transmission scheduling is largely manually configured and routes are determined by a static contact routing graph. A high level of variability exists among the requirements and environmental characteristics of different missions, some of which may allow for the use of more opportunistic routing methods. In all cases, resource allocation and constraints must be balanced with the optimization of data throughput and quality of service. Much work has been done researching routing techniques for terrestrial-based challenged networks in an attempt to optimize contact opportunities and resource usage. This paper examines several popular methods to determine their potential applicability to space networks.

Bio-Inspired Microsystem for Robust Genetic Assay Recognition

PubMed Central

Lue, Jaw-Chyng; Fang, Wai-Chi

2008-01-01

A compact integrated system-on-chip (SoC) architecture solution for robust, real-time, and on-site genetic analysis has been proposed. This microsystem solution is noise-tolerable and suitable for analyzing the weak fluorescence patterns from a PCR prepared dual-labeled DNA microchip assay. In the architecture, a preceding VLSI differential logarithm microchip is designed for effectively computing the logarithm of the normalized input fluorescence signals. A posterior VLSI artificial neural network (ANN) processor chip is used for analyzing the processed signals from the differential logarithm stage. A single-channel logarithmic circuit was fabricated and characterized. A prototype ANN chip with unsupervised winner-take-all (WTA) function was designed, fabricated, and tested. An ANN learning algorithm using a novel sigmoid-logarithmic transfer function based on the supervised backpropagation (BP) algorithm is proposed for robustly recognizing low-intensity patterns. Our results show that the trained new ANN can recognize low-fluorescence patterns better than an ANN using the conventional sigmoid function. PMID:18566679

Conduction Delay Learning Model for Unsupervised and Supervised Classification of Spatio-Temporal Spike Patterns

PubMed Central

Matsubara, Takashi

2017-01-01

Precise spike timing is considered to play a fundamental role in communications and signal processing in biological neural networks. Understanding the mechanism of spike timing adjustment would deepen our understanding of biological systems and enable advanced engineering applications such as efficient computational architectures. However, the biological mechanisms that adjust and maintain spike timing remain unclear. Existing algorithms adopt a supervised approach, which adjusts the axonal conduction delay and synaptic efficacy until the spike timings approximate the desired timings. This study proposes a spike timing-dependent learning model that adjusts the axonal conduction delay and synaptic efficacy in both unsupervised and supervised manners. The proposed learning algorithm approximates the Expectation-Maximization algorithm, and classifies the input data encoded into spatio-temporal spike patterns. Even in the supervised classification, the algorithm requires no external spikes indicating the desired spike timings unlike existing algorithms. Furthermore, because the algorithm is consistent with biological models and hypotheses found in existing biological studies, it could capture the mechanism underlying biological delay learning. PMID:29209191

Conduction Delay Learning Model for Unsupervised and Supervised Classification of Spatio-Temporal Spike Patterns.

PubMed

Matsubara, Takashi

2017-01-01

Precise spike timing is considered to play a fundamental role in communications and signal processing in biological neural networks. Understanding the mechanism of spike timing adjustment would deepen our understanding of biological systems and enable advanced engineering applications such as efficient computational architectures. However, the biological mechanisms that adjust and maintain spike timing remain unclear. Existing algorithms adopt a supervised approach, which adjusts the axonal conduction delay and synaptic efficacy until the spike timings approximate the desired timings. This study proposes a spike timing-dependent learning model that adjusts the axonal conduction delay and synaptic efficacy in both unsupervised and supervised manners. The proposed learning algorithm approximates the Expectation-Maximization algorithm, and classifies the input data encoded into spatio-temporal spike patterns. Even in the supervised classification, the algorithm requires no external spikes indicating the desired spike timings unlike existing algorithms. Furthermore, because the algorithm is consistent with biological models and hypotheses found in existing biological studies, it could capture the mechanism underlying biological delay learning.

A hybrid neural networks-fuzzy logic-genetic algorithm for grade estimation

NASA Astrophysics Data System (ADS)

Tahmasebi, Pejman; Hezarkhani, Ardeshir

2012-05-01

The grade estimation is a quite important and money/time-consuming stage in a mine project, which is considered as a challenge for the geologists and mining engineers due to the structural complexities in mineral ore deposits. To overcome this problem, several artificial intelligence techniques such as Artificial Neural Networks (ANN) and Fuzzy Logic (FL) have recently been employed with various architectures and properties. However, due to the constraints of both methods, they yield the desired results only under the specific circumstances. As an example, one major problem in FL is the difficulty of constructing the membership functions (MFs).Other problems such as architecture and local minima could also be located in ANN designing. Therefore, a new methodology is presented in this paper for grade estimation. This method which is based on ANN and FL is called "Coactive Neuro-Fuzzy Inference System" (CANFIS) which combines two approaches, ANN and FL. The combination of these two artificial intelligence approaches is achieved via the verbal and numerical power of intelligent systems. To improve the performance of this system, a Genetic Algorithm (GA) - as a well-known technique to solve the complex optimization problems - is also employed to optimize the network parameters including learning rate, momentum of the network and the number of MFs for each input. A comparison of these techniques (ANN, Adaptive Neuro-Fuzzy Inference System or ANFIS) with this new method (CANFIS-GA) is also carried out through a case study in Sungun copper deposit, located in East-Azerbaijan, Iran. The results show that CANFIS-GA could be a faster and more accurate alternative to the existing time-consuming methodologies for ore grade estimation and that is, therefore, suggested to be applied for grade estimation in similar problems.

A hybrid neural networks-fuzzy logic-genetic algorithm for grade estimation

PubMed Central

Tahmasebi, Pejman; Hezarkhani, Ardeshir

2012-01-01

The grade estimation is a quite important and money/time-consuming stage in a mine project, which is considered as a challenge for the geologists and mining engineers due to the structural complexities in mineral ore deposits. To overcome this problem, several artificial intelligence techniques such as Artificial Neural Networks (ANN) and Fuzzy Logic (FL) have recently been employed with various architectures and properties. However, due to the constraints of both methods, they yield the desired results only under the specific circumstances. As an example, one major problem in FL is the difficulty of constructing the membership functions (MFs).Other problems such as architecture and local minima could also be located in ANN designing. Therefore, a new methodology is presented in this paper for grade estimation. This method which is based on ANN and FL is called “Coactive Neuro-Fuzzy Inference System” (CANFIS) which combines two approaches, ANN and FL. The combination of these two artificial intelligence approaches is achieved via the verbal and numerical power of intelligent systems. To improve the performance of this system, a Genetic Algorithm (GA) – as a well-known technique to solve the complex optimization problems – is also employed to optimize the network parameters including learning rate, momentum of the network and the number of MFs for each input. A comparison of these techniques (ANN, Adaptive Neuro-Fuzzy Inference System or ANFIS) with this new method (CANFIS–GA) is also carried out through a case study in Sungun copper deposit, located in East-Azerbaijan, Iran. The results show that CANFIS–GA could be a faster and more accurate alternative to the existing time-consuming methodologies for ore grade estimation and that is, therefore, suggested to be applied for grade estimation in similar problems. PMID:25540468

MONGKIE: an integrated tool for network analysis and visualization for multi-omics data.

PubMed

Jang, Yeongjun; Yu, Namhee; Seo, Jihae; Kim, Sun; Lee, Sanghyuk

2016-03-18

Network-based integrative analysis is a powerful technique for extracting biological insights from multilayered omics data such as somatic mutations, copy number variations, and gene expression data. However, integrated analysis of multi-omics data is quite complicated and can hardly be done in an automated way. Thus, a powerful interactive visual mining tool supporting diverse analysis algorithms for identification of driver genes and regulatory modules is much needed. Here, we present a software platform that integrates network visualization with omics data analysis tools seamlessly. The visualization unit supports various options for displaying multi-omics data as well as unique network models for describing sophisticated biological networks such as complex biomolecular reactions. In addition, we implemented diverse in-house algorithms for network analysis including network clustering and over-representation analysis. Novel functions include facile definition and optimized visualization of subgroups, comparison of a series of data sets in an identical network by data-to-visual mapping and subsequent overlaying function, and management of custom interaction networks. Utility of MONGKIE for network-based visual data mining of multi-omics data was demonstrated by analysis of the TCGA glioblastoma data. MONGKIE was developed in Java based on the NetBeans plugin architecture, thus being OS-independent with intrinsic support of module extension by third-party developers. We believe that MONGKIE would be a valuable addition to network analysis software by supporting many unique features and visualization options, especially for analysing multi-omics data sets in cancer and other diseases. .

Scalable Algorithms for Clustering Large Geospatiotemporal Data Sets on Manycore Architectures

NASA Astrophysics Data System (ADS)

Mills, R. T.; Hoffman, F. M.; Kumar, J.; Sreepathi, S.; Sripathi, V.

2016-12-01

The increasing availability of high-resolution geospatiotemporal data sets from sources such as observatory networks, remote sensing platforms, and computational Earth system models has opened new possibilities for knowledge discovery using data sets fused from disparate sources. Traditional algorithms and computing platforms are impractical for the analysis and synthesis of data sets of this size; however, new algorithmic approaches that can effectively utilize the complex memory hierarchies and the extremely high levels of available parallelism in state-of-the-art high-performance computing platforms can enable such analysis. We describe a massively parallel implementation of accelerated k-means clustering and some optimizations to boost computational intensity and utilization of wide SIMD lanes on state-of-the art multi- and manycore processors, including the second-generation Intel Xeon Phi ("Knights Landing") processor based on the Intel Many Integrated Core (MIC) architecture, which includes several new features, including an on-package high-bandwidth memory. We also analyze the code in the context of a few practical applications to the analysis of climatic and remotely-sensed vegetation phenology data sets, and speculate on some of the new applications that such scalable analysis methods may enable.

P2MP MPLS-Based Hierarchical Service Management System

NASA Astrophysics Data System (ADS)

Kumaki, Kenji; Nakagawa, Ikuo; Nagami, Kenichi; Ogishi, Tomohiko; Ano, Shigehiro

This paper proposes a point-to-multipoint (P2MP) Multi-Protocol Label Switching (MPLS) based hierarchical service management system. Traditionally, general management systems deployed in some service providers control MPLS Label Switched Paths (LSPs) (e.g., RSVP-TE and LDP) and services (e.g., L2VPN, L3VPN and IP) separately. In order for dedicated management systems for MPLS LSPs and services to cooperate with each other automatically, a hierarchical service management system has been proposed with the main focus on point-to-point (P2P) TE LSPs in MPLS path management. In the case where P2MP TE LSPs and services are deployed in MPLS networks, the dedicated management systems for P2MP TE LSPs and services must work together automatically. Therefore, this paper proposes a new algorithm that uses a correlation between P2MP TE LSPs and multicast VPN services based on a P2MP MPLS-based hierarchical service management architecture. Also, the capacity and performance of the proposed algorithm are evaluated by simulations, which are actually based on certain real MPLS production networks, and are compared to that of the algorithm for P2P TE LSPs. Results show this system is very scalable within real MPLS production networks. This system, with the automatic correlation, appears to be deployable in real MPLS production networks.

A novel PON-based mobile distributed cluster of antennas approach to provide impartial and broadband services to end users

NASA Astrophysics Data System (ADS)

Sana, Ajaz; Saddawi, Samir; Moghaddassi, Jalil; Hussain, Shahab; Zaidi, Syed R.

2010-01-01

In this research paper we propose a novel Passive Optical Network (PON) based Mobile Worldwide Interoperability for Microwave Access (WiMAX) access network architecture to provide high capacity and performance multimedia services to mobile WiMAX users. Passive Optical Networks (PON) networks do not require powered equipment; hence they cost lower and need less network management. WiMAX technology emerges as a viable candidate for the last mile solution. In the conventional WiMAX access networks, the base stations and Multiple Input Multiple Output (MIMO) antennas are connected by point to point lines. Ideally in theory, the Maximum WiMAX bandwidth is assumed to be 70 Mbit/s over 31 miles. In reality, WiMAX can only provide one or the other as when operating over maximum range, bit error rate increases and therefore it is required to use lower bit rate. Lowering the range allows a device to operate at higher bit rates. Our focus in this research paper is to increase both range and bit rate by utilizing distributed cluster of MIMO antennas connected to WiMAX base stations with PON based topologies. A novel quality of service (QoS) algorithm is also proposed to provide admission control and scheduling to serve classified traffic. The proposed architecture presents flexible and scalable system design with different performance requirements and complexity.

The architecture of the management system of complex steganographic information

NASA Astrophysics Data System (ADS)

Evsutin, O. O.; Meshcheryakov, R. V.; Kozlova, A. S.; Solovyev, T. M.

2017-01-01

The aim of the study is to create a wide area information system that allows one to control processes of generation, embedding, extraction, and detection of steganographic information. In this paper, the following problems are considered: the definition of the system scope and the development of its architecture. For creation of algorithmic maintenance of the system, classic methods of steganography are used to embed information. Methods of mathematical statistics and computational intelligence are used to identify the embedded information. The main result of the paper is the development of the architecture of the management system of complex steganographic information. The suggested architecture utilizes cloud technology in order to provide service using the web-service via the Internet. It is meant to provide streams of multimedia data processing that are streams with many sources of different types. The information system, built in accordance with the proposed architecture, will be used in the following areas: hidden transfer of documents protected by medical secrecy in telemedicine systems; copyright protection of online content in public networks; prevention of information leakage caused by insiders.

A smart phone-based pocket fall accident detection, positioning, and rescue system.

PubMed

Kau, Lih-Jen; Chen, Chih-Sheng

2015-01-01

We propose in this paper a novel algorithm as well as architecture for the fall accident detection and corresponding wide area rescue system based on a smart phone and the third generation (3G) networks. To realize the fall detection algorithm, the angles acquired by the electronic compass (ecompass) and the waveform sequence of the triaxial accelerometer on the smart phone are used as the system inputs. The acquired signals are then used to generate an ordered feature sequence and then examined in a sequential manner by the proposed cascade classifier for recognition purpose. Once the corresponding feature is verified by the classifier at current state, it can proceed to next state; otherwise, the system will reset to the initial state and wait for the appearance of another feature sequence. Once a fall accident event is detected, the user's position can be acquired by the global positioning system (GPS) or the assisted GPS, and sent to the rescue center via the 3G communication network so that the user can get medical help immediately. With the proposed cascaded classification architecture, the computational burden and power consumption issue on the smart phone system can be alleviated. Moreover, as we will see in the experiment that a distinguished fall accident detection accuracy up to 92% on the sensitivity and 99.75% on the specificity can be obtained when a set of 450 test actions in nine different kinds of activities are estimated by using the proposed cascaded classifier, which justifies the superiority of the proposed algorithm.

High-efficiency space-based software radio architectures & algorithms (a minimum size, weight, and power TeraOps processor)

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

Dunham, Mark Edward; Baker, Zachary K; Stettler, Matthew W

2009-01-01

Los Alamos has recently completed the latest in a series of Reconfigurable Software Radios, which incorporates several key innovations in both hardware design and algorithms. Due to our focus on satellite applications, each design must extract the best size, weight, and power performance possible from the ensemble of Commodity Off-the-Shelf (COTS) parts available at the time of design. In this case we have achieved 1 TeraOps/second signal processing on a 1920 Megabit/second datastream, while using only 53 Watts mains power, 5.5 kg, and 3 liters. This processing capability enables very advanced algorithms such as our wideband RF compression scheme tomore » operate remotely, allowing network bandwidth constrained applications to deliver previously unattainable performance.« less

Comments on "The multisynapse neural network and its application to fuzzy clustering".

PubMed

Yu, Jian; Hao, Pengwei

2005-05-01

In the above-mentioned paper, Wei and Fahn proposed a neural architecture, the multisynapse neural network, to solve constrained optimization problems including high-order, logarithmic, and sinusoidal forms, etc. As one of its main applications, a fuzzy bidirectional associative clustering network (FBACN) was proposed for fuzzy-partition clustering according to the objective-functional method. The connection between the objective-functional-based fuzzy c-partition algorithms and FBACN is the Lagrange multiplier approach. Unfortunately, the Lagrange multiplier approach was incorrectly applied so that FBACN does not equivalently minimize its corresponding constrained objective-function. Additionally, Wei and Fahn adopted traditional definition of fuzzy c-partition, which is not satisfied by FBACN. Therefore, FBACN can not solve constrained optimization problems, either.

The HEP.TrkX Project: deep neural networks for HL-LHC online and offline tracking

DOE PAGES

Farrell, Steven; Anderson, Dustin; Calafiura, Paolo; ...

2017-08-08

Particle track reconstruction in dense environments such as the detectors of the High Luminosity Large Hadron Collider (HL-LHC) is a challenging pattern recognition problem. Traditional tracking algorithms such as the combinatorial Kalman Filter have been used with great success in LHC experiments for years. However, these state-of-the-art techniques are inherently sequential and scale poorly with the expected increases in detector occupancy in the HL-LHC conditions. The HEP.TrkX project is a pilot project with the aim to identify and develop cross-experiment solutions based on machine learning algorithms for track reconstruction. Machine learning algorithms bring a lot of potential to this problemmore » thanks to their capability to model complex non-linear data dependencies, to learn effective representations of high-dimensional data through training, and to parallelize easily on high-throughput architectures such as GPUs. This contribution will describe our initial explorations into this relatively unexplored idea space. Furthermore, we will discuss the use of recurrent (LSTM) and convolutional neural networks to find and fit tracks in toy detector data.« less

The HEP.TrkX Project: deep neural networks for HL-LHC online and offline tracking

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

Farrell, Steven; Anderson, Dustin; Calafiura, Paolo

Particle track reconstruction in dense environments such as the detectors of the High Luminosity Large Hadron Collider (HL-LHC) is a challenging pattern recognition problem. Traditional tracking algorithms such as the combinatorial Kalman Filter have been used with great success in LHC experiments for years. However, these state-of-the-art techniques are inherently sequential and scale poorly with the expected increases in detector occupancy in the HL-LHC conditions. The HEP.TrkX project is a pilot project with the aim to identify and develop cross-experiment solutions based on machine learning algorithms for track reconstruction. Machine learning algorithms bring a lot of potential to this problemmore » thanks to their capability to model complex non-linear data dependencies, to learn effective representations of high-dimensional data through training, and to parallelize easily on high-throughput architectures such as GPUs. This contribution will describe our initial explorations into this relatively unexplored idea space. Furthermore, we will discuss the use of recurrent (LSTM) and convolutional neural networks to find and fit tracks in toy detector data.« less

The HEP.TrkX Project: deep neural networks for HL-LHC online and offline tracking

NASA Astrophysics Data System (ADS)

Farrell, Steven; Anderson, Dustin; Calafiura, Paolo; Cerati, Giuseppe; Gray, Lindsey; Kowalkowski, Jim; Mudigonda, Mayur; Prabhat; Spentzouris, Panagiotis; Spiropoulou, Maria; Tsaris, Aristeidis; Vlimant, Jean-Roch; Zheng, Stephan

2017-08-01

Particle track reconstruction in dense environments such as the detectors of the High Luminosity Large Hadron Collider (HL-LHC) is a challenging pattern recognition problem. Traditional tracking algorithms such as the combinatorial Kalman Filter have been used with great success in LHC experiments for years. However, these state-of-the-art techniques are inherently sequential and scale poorly with the expected increases in detector occupancy in the HL-LHC conditions. The HEP.TrkX project is a pilot project with the aim to identify and develop cross-experiment solutions based on machine learning algorithms for track reconstruction. Machine learning algorithms bring a lot of potential to this problem thanks to their capability to model complex non-linear data dependencies, to learn effective representations of high-dimensional data through training, and to parallelize easily on high-throughput architectures such as GPUs. This contribution will describe our initial explorations into this relatively unexplored idea space. We will discuss the use of recurrent (LSTM) and convolutional neural networks to find and fit tracks in toy detector data.

Design of an Efficient CAC for a Broadband DVB-S/DVB-RCS Satellite Access Network

NASA Astrophysics Data System (ADS)

Inzerilli, Tiziano; Montozzi, Simone

2003-07-01

This paper deals with efficient utilization of network resources in an advanced broadband satellite access system. It proposes a technique for admission control of IP streams with guaranteed QoS which does not interfere with the particular BoD (Bandwidth on Demand) algorithm that handles access to uplink bandwidth, an essential part of a DVB- RCS architecture. This feature of the admission control greatly simplify its integration in the satellite network. The purpose of this admission control algorithm in particular is to suitably and dynamically configure the overall traffic control parameters, in the access terminal of the user and service segment, with a simple approach which does not introduces limitations and/or constraints to the BoD algorithm. Performance of the proposed algorithm is evaluated thorugh Opnet simulations using an ad-hoc platform modeling DVB-based satellite access.The results presented in this paper were obtained within SATIP6 project, which is sponsored within the 5th EU Research Programme, IST. The aims of the project are to evaluate and demonstrate key issues of the integration of satellite-based access networks into the Internet in order to support multimedia services over wide areas. The satellite link layer is based on DVB-S on the forward link and DVB-RCS on the return link. Adaptation and optimization of the DVB-RCS access standard in order to support QoS provision are central issues of the project. They are handled through an integration of Connection Admission Control (CAC), Traffic Shaping and Policing techniques.

Modular Toolkit for Data Processing (MDP): A Python Data Processing Framework.

PubMed

Zito, Tiziano; Wilbert, Niko; Wiskott, Laurenz; Berkes, Pietro

2008-01-01

Modular toolkit for Data Processing (MDP) is a data processing framework written in Python. From the user's perspective, MDP is a collection of supervised and unsupervised learning algorithms and other data processing units that can be combined into data processing sequences and more complex feed-forward network architectures. Computations are performed efficiently in terms of speed and memory requirements. From the scientific developer's perspective, MDP is a modular framework, which can easily be expanded. The implementation of new algorithms is easy and intuitive. The new implemented units are then automatically integrated with the rest of the library. MDP has been written in the context of theoretical research in neuroscience, but it has been designed to be helpful in any context where trainable data processing algorithms are used. Its simplicity on the user's side, the variety of readily available algorithms, and the reusability of the implemented units make it also a useful educational tool.

Dawn: A Simulation Model for Evaluating Costs and Tradeoffs of Big Data Science Architectures

NASA Astrophysics Data System (ADS)

Cinquini, L.; Crichton, D. J.; Braverman, A. J.; Kyo, L.; Fuchs, T.; Turmon, M.

2014-12-01

In many scientific disciplines, scientists and data managers are bracing for an upcoming deluge of big data volumes, which will increase the size of current data archives by a factor of 10-100 times. For example, the next Climate Model Inter-comparison Project (CMIP6) will generate a global archive of model output of approximately 10-20 Peta-bytes, while the upcoming next generation of NASA decadal Earth Observing instruments are expected to collect tens of Giga-bytes/day. In radio-astronomy, the Square Kilometre Array (SKA) will collect data in the Exa-bytes/day range, of which (after reduction and processing) around 1.5 Exa-bytes/year will be stored. The effective and timely processing of these enormous data streams will require the design of new data reduction and processing algorithms, new system architectures, and new techniques for evaluating computation uncertainty. Yet at present no general software tool or framework exists that will allow system architects to model their expected data processing workflow, and determine the network, computational and storage resources needed to prepare their data for scientific analysis. In order to fill this gap, at NASA/JPL we have been developing a preliminary model named DAWN (Distributed Analytics, Workflows and Numerics) for simulating arbitrary complex workflows composed of any number of data processing and movement tasks. The model can be configured with a representation of the problem at hand (the data volumes, the processing algorithms, the available computing and network resources), and is able to evaluate tradeoffs between different possible workflows based on several estimators: overall elapsed time, separate computation and transfer times, resulting uncertainty, and others. So far, we have been applying DAWN to analyze architectural solutions for 4 different use cases from distinct science disciplines: climate science, astronomy, hydrology and a generic cloud computing use case. This talk will present preliminary results and discuss how DAWN can be evolved into a powerful tool for designing system architectures for data intensive science.

Design and Analysis of Self-Adapted Task Scheduling Strategies in Wireless Sensor Networks

PubMed Central

Guo, Wenzhong; Xiong, Naixue; Chao, Han-Chieh; Hussain, Sajid; Chen, Guolong

2011-01-01

In a wireless sensor network (WSN), the usage of resources is usually highly related to the execution of tasks which consume a certain amount of computing and communication bandwidth. Parallel processing among sensors is a promising solution to provide the demanded computation capacity in WSNs. Task allocation and scheduling is a typical problem in the area of high performance computing. Although task allocation and scheduling in wired processor networks has been well studied in the past, their counterparts for WSNs remain largely unexplored. Existing traditional high performance computing solutions cannot be directly implemented in WSNs due to the limitations of WSNs such as limited resource availability and the shared communication medium. In this paper, a self-adapted task scheduling strategy for WSNs is presented. First, a multi-agent-based architecture for WSNs is proposed and a mathematical model of dynamic alliance is constructed for the task allocation problem. Then an effective discrete particle swarm optimization (PSO) algorithm for the dynamic alliance (DPSO-DA) with a well-designed particle position code and fitness function is proposed. A mutation operator which can effectively improve the algorithm’s ability of global search and population diversity is also introduced in this algorithm. Finally, the simulation results show that the proposed solution can achieve significant better performance than other algorithms. PMID:22163971

Sensor Network Architectures for Monitoring Underwater Pipelines

PubMed Central

Mohamed, Nader; Jawhar, Imad; Al-Jaroodi, Jameela; Zhang, Liren

2011-01-01

This paper develops and compares different sensor network architecture designs that can be used for monitoring underwater pipeline infrastructures. These architectures are underwater wired sensor networks, underwater acoustic wireless sensor networks, RF (Radio Frequency) wireless sensor networks, integrated wired/acoustic wireless sensor networks, and integrated wired/RF wireless sensor networks. The paper also discusses the reliability challenges and enhancement approaches for these network architectures. The reliability evaluation, characteristics, advantages, and disadvantages among these architectures are discussed and compared. Three reliability factors are used for the discussion and comparison: the network connectivity, the continuity of power supply for the network, and the physical network security. In addition, the paper also develops and evaluates a hierarchical sensor network framework for underwater pipeline monitoring. PMID:22346669

Sensor network architectures for monitoring underwater pipelines.

PubMed

Mohamed, Nader; Jawhar, Imad; Al-Jaroodi, Jameela; Zhang, Liren

2011-01-01

This paper develops and compares different sensor network architecture designs that can be used for monitoring underwater pipeline infrastructures. These architectures are underwater wired sensor networks, underwater acoustic wireless sensor networks, RF (radio frequency) wireless sensor networks, integrated wired/acoustic wireless sensor networks, and integrated wired/RF wireless sensor networks. The paper also discusses the reliability challenges and enhancement approaches for these network architectures. The reliability evaluation, characteristics, advantages, and disadvantages among these architectures are discussed and compared. Three reliability factors are used for the discussion and comparison: the network connectivity, the continuity of power supply for the network, and the physical network security. In addition, the paper also develops and evaluates a hierarchical sensor network framework for underwater pipeline monitoring.

Diamond Eye: a distributed architecture for image data mining

NASA Astrophysics Data System (ADS)

Burl, Michael C.; Fowlkes, Charless; Roden, Joe; Stechert, Andre; Mukhtar, Saleem

1999-02-01

Diamond Eye is a distributed software architecture, which enables users (scientists) to analyze large image collections by interacting with one or more custom data mining servers via a Java applet interface. Each server is coupled with an object-oriented database and a computational engine, such as a network of high-performance workstations. The database provides persistent storage and supports querying of the 'mined' information. The computational engine provides parallel execution of expensive image processing, object recognition, and query-by-content operations. Key benefits of the Diamond Eye architecture are: (1) the design promotes trial evaluation of advanced data mining and machine learning techniques by potential new users (all that is required is to point a web browser to the appropriate URL), (2) software infrastructure that is common across a range of science mining applications is factored out and reused, and (3) the system facilitates closer collaborations between algorithm developers and domain experts.

Can surgical simulation be used to train detection and classification of neural networks?

PubMed

Zisimopoulos, Odysseas; Flouty, Evangello; Stacey, Mark; Muscroft, Sam; Giataganas, Petros; Nehme, Jean; Chow, Andre; Stoyanov, Danail

2017-10-01

Computer-assisted interventions (CAI) aim to increase the effectiveness, precision and repeatability of procedures to improve surgical outcomes. The presence and motion of surgical tools is a key information input for CAI surgical phase recognition algorithms. Vision-based tool detection and recognition approaches are an attractive solution and can be designed to take advantage of the powerful deep learning paradigm that is rapidly advancing image recognition and classification. The challenge for such algorithms is the availability and quality of labelled data used for training. In this Letter, surgical simulation is used to train tool detection and segmentation based on deep convolutional neural networks and generative adversarial networks. The authors experiment with two network architectures for image segmentation in tool classes commonly encountered during cataract surgery. A commercially-available simulator is used to create a simulated cataract dataset for training models prior to performing transfer learning on real surgical data. To the best of authors' knowledge, this is the first attempt to train deep learning models for surgical instrument detection on simulated data while demonstrating promising results to generalise on real data. Results indicate that simulated data does have some potential for training advanced classification methods for CAI systems.

Fast, Simple and Accurate Handwritten Digit Classification by Training Shallow Neural Network Classifiers with the ‘Extreme Learning Machine’ Algorithm

PubMed Central

McDonnell, Mark D.; Tissera, Migel D.; Vladusich, Tony; van Schaik, André; Tapson, Jonathan

2015-01-01

Recent advances in training deep (multi-layer) architectures have inspired a renaissance in neural network use. For example, deep convolutional networks are becoming the default option for difficult tasks on large datasets, such as image and speech recognition. However, here we show that error rates below 1% on the MNIST handwritten digit benchmark can be replicated with shallow non-convolutional neural networks. This is achieved by training such networks using the ‘Extreme Learning Machine’ (ELM) approach, which also enables a very rapid training time (∼ 10 minutes). Adding distortions, as is common practise for MNIST, reduces error rates even further. Our methods are also shown to be capable of achieving less than 5.5% error rates on the NORB image database. To achieve these results, we introduce several enhancements to the standard ELM algorithm, which individually and in combination can significantly improve performance. The main innovation is to ensure each hidden-unit operates only on a randomly sized and positioned patch of each image. This form of random ‘receptive field’ sampling of the input ensures the input weight matrix is sparse, with about 90% of weights equal to zero. Furthermore, combining our methods with a small number of iterations of a single-batch backpropagation method can significantly reduce the number of hidden-units required to achieve a particular performance. Our close to state-of-the-art results for MNIST and NORB suggest that the ease of use and accuracy of the ELM algorithm for designing a single-hidden-layer neural network classifier should cause it to be given greater consideration either as a standalone method for simpler problems, or as the final classification stage in deep neural networks applied to more difficult problems. PMID:26262687

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.).

Scaling Deep Learning workloads: NVIDIA DGX-1/Pascal and Intel Knights Landing

DOE PAGES

Gawande, Nitin A.; Daily, Jeff A.; Siegel, Charles; ...

2018-05-05

Deep Learning (DL) algorithms have become ubiquitous in data analytics. As a result, major computing vendors—including NVIDIA, Intel, AMD, and IBM—have architectural road maps influenced by DL workloads. Furthermore, several vendors have recently advertised new computing products as accelerating large DL workloads. Unfortunately, it is difficult for data scientists to quantify the potential of these different products. Here, this article provides a performance and power analysis of important DL workloads on two major parallel architectures: NVIDIA DGX-1 (eight Pascal P100 GPUs interconnected with NVLink) and Intel Knights Landing (KNL) CPUs interconnected with Intel Omni-Path or Cray Aries. Our evaluation consistsmore » of a cross section of convolutional neural net workloads: CifarNet, AlexNet, GoogLeNet, and ResNet50 topologies using the Cifar10 and ImageNet datasets. The workloads are vendor-optimized for each architecture. We use sequentially equivalent implementations to maintain iso-accuracy between parallel and sequential DL models. Our analysis indicates that although GPUs provide the highest overall performance, the gap can close for some convolutional networks; and the KNL can be competitive in performance/watt. We find that NVLink facilitates scaling efficiency on GPUs. However, its importance is heavily dependent on neural network architecture. Furthermore, for weak-scaling—sometimes encouraged by restricted GPU memory—NVLink is less important.« less

Scaling Deep Learning workloads: NVIDIA DGX-1/Pascal and Intel Knights Landing

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

Gawande, Nitin A.; Daily, Jeff A.; Siegel, Charles

Deep Learning (DL) algorithms have become ubiquitous in data analytics. As a result, major computing vendors—including NVIDIA, Intel, AMD, and IBM—have architectural road maps influenced by DL workloads. Furthermore, several vendors have recently advertised new computing products as accelerating large DL workloads. Unfortunately, it is difficult for data scientists to quantify the potential of these different products. Here, this article provides a performance and power analysis of important DL workloads on two major parallel architectures: NVIDIA DGX-1 (eight Pascal P100 GPUs interconnected with NVLink) and Intel Knights Landing (KNL) CPUs interconnected with Intel Omni-Path or Cray Aries. Our evaluation consistsmore » of a cross section of convolutional neural net workloads: CifarNet, AlexNet, GoogLeNet, and ResNet50 topologies using the Cifar10 and ImageNet datasets. The workloads are vendor-optimized for each architecture. We use sequentially equivalent implementations to maintain iso-accuracy between parallel and sequential DL models. Our analysis indicates that although GPUs provide the highest overall performance, the gap can close for some convolutional networks; and the KNL can be competitive in performance/watt. We find that NVLink facilitates scaling efficiency on GPUs. However, its importance is heavily dependent on neural network architecture. Furthermore, for weak-scaling—sometimes encouraged by restricted GPU memory—NVLink is less important.« less

Research on performance of three-layer MG-OXC system based on MLAG and OCDM

NASA Astrophysics Data System (ADS)

Wang, Yubao; Ren, Yanfei; Meng, Ying; Bai, Jian

2017-10-01

At present, as traffic volume which optical transport networks convey and species of traffic grooming methods increase rapidly, optical switching techniques are faced with a series of issues, such as more requests for the number of wavelengths and complicated structure management and implementation. This work introduces optical code switching based on wavelength switching, constructs the three layers multi-granularity optical cross connection (MG-OXC) system on the basis of optical code division multiplexing (OCDM) and presents a new traffic grooming algorithm. The proposed architecture can improve the flexibility of traffic grooming, reduce the amount of used wavelengths and save the number of consumed ports, hence, it can simplify routing device and enhance the performance of the system significantly. Through analyzing the network model of switching structure on multicast layered auxiliary graph (MLAG) and the establishment of traffic grooming links, and the simulation of blocking probability and throughput, this paper shows the excellent performance of this mentioned architecture.

Design and Implementation of a Lunar Communications Satellite and Server for the 2012 SISO Smackdown

NASA Technical Reports Server (NTRS)

Bulgatz, Dennis; Heater, Daniel; O'Neal, Daniel A.; Norris, Bryan; Schricker, Bradley C.

2012-01-01

Last year, the Simulation Interoperability Standards Organization (SISO) inaugurated the now annual High Level Architecture (HLA) Smackdown at the Spring Simulation Interoperability Workshop (SIW). A primary objective of the Smackdown event is to provide college students with hands-on experience in the High Level Architecture (HLA). The University of Alabama in Huntsville (UAHuntsville) fielded teams in 2011 and 2012. Both the 2011 and 2012 smackdown scenarios were a lunar resupply mission. The 2012 UAHuntsville fielded four federates: a communications network Federate called Lunar Communications and Navigation Satellite Service (LCANServ) for sending and receiving messages, a Lunar Satellite Constellation (LCANSat) to put in place radios needed by the communications network for Line-Of-Sight communication calculations, and 3D graphical displays of the orbiting satellites and a 3D visualization of the lunar surface activities. This paper concentrates on the first two federates by describing the functions, algorithms, the modular FOM, experiences, lessons learned and recommendations for future Smackdown events.

Robust artificial intelligence tool for automatic start-up of the supplementary medium feeding in recombinant E. coli cultivations.

PubMed

Horta, Antônio Carlos Luperni; da Silva, Adilson José; Sargo, Cíntia Regina; Gonçalves, Viviane Maimoni; Zangirolami, Teresa Cristina; Giordano, Roberto de Campos

2011-09-01

One of the most important events in fed-batch fermentations is the definition of the moment to start the feeding. This paper presents a methodology for a rational selection of the architecture of an artificial intelligence (AI) system, based on a neural network committee (NNC), which identifies the end of the batch phase. The AI system was successfully used during high cell density cultivations of recombinant Escherichia coli. The AI algorithm was validated for different systems, expressing three antigens to be used in human and animal vaccines: fragments of surface proteins of Streptococcus pneumoniae (PspA), clades 1 and 3, and of Erysipelothrix rhusiopathiae (SpaA). Standard feed-forward neural networks (NNs), with a single hidden layer, were the basis for the NNC. The NN architecture with best performance had the following inputs: stirrer speed, inlet air, and oxygen flow rates, carbon dioxide evolution rate, and CO2 molar fraction in the exhaust gas.

A Parallel Rendering Algorithm for MIMD Architectures

NASA Technical Reports Server (NTRS)

Crockett, Thomas W.; Orloff, Tobias

1991-01-01

Applications such as animation and scientific visualization demand high performance rendering of complex three dimensional scenes. To deliver the necessary rendering rates, highly parallel hardware architectures are required. The challenge is then to design algorithms and software which effectively use the hardware parallelism. A rendering algorithm targeted to distributed memory MIMD architectures is described. For maximum performance, the algorithm exploits both object-level and pixel-level parallelism. The behavior of the algorithm is examined both analytically and experimentally. Its performance for large numbers of processors is found to be limited primarily by communication overheads. An experimental implementation for the Intel iPSC/860 shows increasing performance from 1 to 128 processors across a wide range of scene complexities. It is shown that minimal modifications to the algorithm will adapt it for use on shared memory architectures as well.

Strategies for concurrent processing of complex algorithms in data driven architectures

NASA Technical Reports Server (NTRS)

Stoughton, John W.; Mielke, Roland R.; Som, Sukhamony

1990-01-01

The performance modeling and enhancement for periodic execution of large-grain, decision-free algorithms in data flow architectures is examined. Applications include real-time implementation of control and signal processing algorithms where performance is required to be highly predictable. The mapping of algorithms onto the specified class of data flow architectures is realized by a marked graph model called ATAMM (Algorithm To Architecture Mapping Model). Performance measures and bounds are established. Algorithm transformation techniques are identified for performance enhancement and reduction of resource (computing element) requirements. A systematic design procedure is described for generating operating conditions for predictable performance both with and without resource constraints. An ATAMM simulator is used to test and validate the performance prediction by the design procedure. Experiments on a three resource testbed provide verification of the ATAMM model and the design procedure.

Strategies for concurrent processing of complex algorithms in data driven architectures

NASA Technical Reports Server (NTRS)

Som, Sukhamoy; Stoughton, John W.; Mielke, Roland R.

1990-01-01

Performance modeling and performance enhancement for periodic execution of large-grain, decision-free algorithms in data flow architectures are discussed. Applications include real-time implementation of control and signal processing algorithms where performance is required to be highly predictable. The mapping of algorithms onto the specified class of data flow architectures is realized by a marked graph model called algorithm to architecture mapping model (ATAMM). Performance measures and bounds are established. Algorithm transformation techniques are identified for performance enhancement and reduction of resource (computing element) requirements. A systematic design procedure is described for generating operating conditions for predictable performance both with and without resource constraints. An ATAMM simulator is used to test and validate the performance prediction by the design procedure. Experiments on a three resource testbed provide verification of the ATAMM model and the design procedure.

Detecting central fixation by means of artificial neural networks in a pediatric vision screener using retinal birefringence scanning.

PubMed

Gramatikov, Boris I

2017-04-27

Reliable detection of central fixation and eye alignment is essential in the diagnosis of amblyopia ("lazy eye"), which can lead to blindness. Our lab has developed and reported earlier a pediatric vision screener that performs scanning of the retina around the fovea and analyzes changes in the polarization state of light as the scan progresses. Depending on the direction of gaze and the instrument design, the screener produces several signal frequencies that can be utilized in the detection of central fixation. The objective of this study was to compare artificial neural networks with classical statistical methods, with respect to their ability to detect central fixation reliably. A classical feedforward, pattern recognition, two-layer neural network architecture was used, consisting of one hidden layer and one output layer. The network has four inputs, representing normalized spectral powers at four signal frequencies generated during retinal birefringence scanning. The hidden layer contains four neurons. The output suggests presence or absence of central fixation. Backpropagation was used to train the network, using the gradient descent algorithm and the cross-entropy error as the performance function. The network was trained, validated and tested on a set of controlled calibration data obtained from 600 measurements from ten eyes in a previous study, and was additionally tested on a clinical set of 78 eyes, independently diagnosed by an ophthalmologist. In the first part of this study, a neural network was designed around the calibration set. With a proper architecture and training, the network provided performance that was comparable to classical statistical methods, allowing perfect separation between the central and paracentral fixation data, with both the sensitivity and the specificity of the instrument being 100%. In the second part of the study, the neural network was applied to the clinical data. It allowed reliable separation between normal subjects and affected subjects, its accuracy again matching that of the statistical methods. With a proper choice of a neural network architecture and a good, uncontaminated training data set, the artificial neural network can be an efficient classification tool for detecting central fixation based on retinal birefringence scanning.

Research of the key technology in satellite communication networks

NASA Astrophysics Data System (ADS)

Zeng, Yuan

2018-02-01

According to the prediction, in the next 10 years the wireless data traffic will be increased by 500-1000 times. Not only the wireless data traffic will be increased exponentially, and the demand for diversified traffic will be increased. Higher requirements for future mobile wireless communication system had brought huge market space for satellite communication system. At the same time, the space information networks had been greatly developed with the depth of human exploration of space activities, the development of space application, the expansion of military and civilian application. The core of spatial information networks is the satellite communication. The dissertation presented the communication system architecture, the communication protocol, the routing strategy, switch scheduling algorithm and the handoff strategy based on the satellite communication system. We built the simulation platform of the LEO satellites networks and simulated the key technology using OPNET.

Wavelet decomposition and radial basis function networks for system monitoring

NASA Astrophysics Data System (ADS)

Ikonomopoulos, A.; Endou, A.

1998-10-01

Two approaches are coupled to develop a novel collection of black box models for monitoring operational parameters in a complex system. The idea springs from the intention of obtaining multiple predictions for each system variable and fusing them before they are used to validate the actual measurement. The proposed architecture pairs the analytical abilities of the discrete wavelet decomposition with the computational power of radial basis function networks. Members of a wavelet family are constructed in a systematic way and chosen through a statistical selection criterion that optimizes the structure of the network. Network parameters are further optimized through a quasi-Newton algorithm. The methodology is demonstrated utilizing data obtained during two transients of the Monju fast breeder reactor. The models developed are benchmarked with respect to similar regressors based on Gaussian basis functions.

Toward a More Robust Pruning Procedure for MLP Networks

NASA Technical Reports Server (NTRS)

Stepniewski, Slawomir W.; Jorgensen, Charles C.

1998-01-01

Choosing a proper neural network architecture is a problem of great practical importance. Smaller models mean not only simpler designs but also lower variance for parameter estimation and network prediction. The widespread utilization of neural networks in modeling highlights an issue in human factors. The procedure of building neural models should find an appropriate level of model complexity in a more or less automatic fashion to make it less prone to human subjectivity. In this paper we present a Singular Value Decomposition based node elimination technique and enhanced implementation of the Optimal Brain Surgeon algorithm. Combining both methods creates a powerful pruning engine that can be used for tuning feedforward connectionist models. The performance of the proposed method is demonstrated by adjusting the structure of a multi-input multi-output model used to calibrate a six-component wind tunnel strain gage.

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.

Flexible and evolutionary optical access networks

NASA Astrophysics Data System (ADS)

Hsueh, Yu-Li

Passive optical networks (PONs) are promising solutions that will open the first-mile bottleneck. Current PONs employ time division multiplexing (TDM) to share bandwidth among users, leading to low cost but limited capacity. In the future, wavelength division multiplexing (WDM) technologies will be deployed to achieve high performance. This dissertation describes several advanced technologies to enhance PON systems. A spectral shaping line coding scheme is developed to allow a simple and cost-effective overlay of high data-rate services in existing PONs, leaving field-deployed fibers and existing services untouched. Spectral shapes of coded signals can be manipulated to adapt to different systems. For a specific tolerable interference level, the optimal line code can be found which maximizes the data throughput. Experiments are conducted to demonstrate and compare several optimized line codes. A novel PON employing dynamic wavelength allocation to provide bandwidth sharing across multiple physical PONs is designed and experimentally demonstrated. Tunable lasers, arrayed waveguide gratings, and coarse/fine filtering combine to create a flexible optical access solution. The network's excellent scalability can bridge the gap between conventional TDM PONs and WDM PONs. Scheduling algorithms with quality of service support are also investigated. Simulation results show that the proposed architecture exhibits significant performance gain over conventional PON systems. Streaming video transmission is demonstrated on the prototype experimental testbed. The powerful architecture is a promising candidate for next-generation optical access networks. A new CDR circuit for receiving the bursty traffic in PONs is designed and analyzed. It detects data transition edges upon arrival of the data burst and quickly selects the best clock phase by a control logic circuit. Then, an analog delay-locked loop (DLL) keeps track of data transitions and removes phase errors throughout the burst. The combination of the fast phase detection mechanism and a feedback loop based on DLL allows both fast response and manageable jitter performance in the burst-mode application. A new efficient numerical algorithm is developed to analyze holey optical fibers. The algorithm has been verified against experimental data, and is exploited to design holey optical fibers optimized for the discrete Raman amplification.

Invariant-feature-based adaptive automatic target recognition in obscured 3D point clouds

NASA Astrophysics Data System (ADS)

Khuon, Timothy; Kershner, Charles; Mattei, Enrico; Alverio, Arnel; Rand, Robert

2014-06-01

Target recognition and classification in a 3D point cloud is a non-trivial process due to the nature of the data collected from a sensor system. The signal can be corrupted by noise from the environment, electronic system, A/D converter, etc. Therefore, an adaptive system with a desired tolerance is required to perform classification and recognition optimally. The feature-based pattern recognition algorithm architecture as described below is particularly devised for solving a single-sensor classification non-parametrically. Feature set is extracted from an input point cloud, normalized, and classifier a neural network classifier. For instance, automatic target recognition in an urban area would require different feature sets from one in a dense foliage area. The figure above (see manuscript) illustrates the architecture of the feature based adaptive signature extraction of 3D point cloud including LIDAR, RADAR, and electro-optical data. This network takes a 3D cluster and classifies it into a specific class. The algorithm is a supervised and adaptive classifier with two modes: the training mode and the performing mode. For the training mode, a number of novel patterns are selected from actual or artificial data. A particular 3D cluster is input to the network as shown above for the decision class output. The network consists of three sequential functional modules. The first module is for feature extraction that extracts the input cluster into a set of singular value features or feature vector. Then the feature vector is input into the feature normalization module to normalize and balance it before being fed to the neural net classifier for the classification. The neural net can be trained by actual or artificial novel data until each trained output reaches the declared output within the defined tolerance. In case new novel data is added after the neural net has been learned, the training is then resumed until the neural net has incrementally learned with the new novel data. The associative memory capability of the neural net enables the incremental learning. The back propagation algorithm or support vector machine can be utilized for the classification and recognition.

A VLSI architecture for simplified arithmetic Fourier transform algorithm

NASA Technical Reports Server (NTRS)

Reed, Irving S.; Shih, Ming-Tang; Truong, T. K.; Hendon, E.; Tufts, D. W.

1992-01-01

The arithmetic Fourier transform (AFT) is a number-theoretic approach to Fourier analysis which has been shown to perform competitively with the classical FFT in terms of accuracy, complexity, and speed. Theorems developed in a previous paper for the AFT algorithm are used here to derive the original AFT algorithm which Bruns found in 1903. This is shown to yield an algorithm of less complexity and of improved performance over certain recent AFT algorithms. A VLSI architecture is suggested for this simplified AFT algorithm. This architecture uses a butterfly structure which reduces the number of additions by 25 percent of that used in the direct method.

A Framework and Toolkit for the Construction of Multimodal Learning Interfaces

DTIC Science & Technology

1998-04-29

human communication modalities in the context of a broad class of applications, specifically those that support state manipulation via parameterized actions. The multimodal semantic model is also the basis for a flexible, domain independent, incrementally trainable multimodal interpretation algorithm based on a connectionist network. The second major contribution is an application framework consisting of reusable components and a modular, distributed system architecture. Multimodal application developers can assemble the components in the framework into a new application,

Training Deep Convolutional Neural Networks with Resistive Cross-Point Devices

PubMed Central

Gokmen, Tayfun; Onen, Murat; Haensch, Wilfried

2017-01-01

In a previous work we have detailed the requirements for obtaining maximal deep learning performance benefit by implementing fully connected deep neural networks (DNN) in the form of arrays of resistive devices. Here we extend the concept of Resistive Processing Unit (RPU) devices to convolutional neural networks (CNNs). We show how to map the convolutional layers to fully connected RPU arrays such that the parallelism of the hardware can be fully utilized in all three cycles of the backpropagation algorithm. We find that the noise and bound limitations imposed by the analog nature of the computations performed on the arrays significantly affect the training accuracy of the CNNs. Noise and bound management techniques are presented that mitigate these problems without introducing any additional complexity in the analog circuits and that can be addressed by the digital circuits. In addition, we discuss digitally programmable update management and device variability reduction techniques that can be used selectively for some of the layers in a CNN. We show that a combination of all those techniques enables a successful application of the RPU concept for training CNNs. The techniques discussed here are more general and can be applied beyond CNN architectures and therefore enables applicability of the RPU approach to a large class of neural network architectures. PMID:29066942

Training Deep Convolutional Neural Networks with Resistive Cross-Point Devices.

PubMed

Gokmen, Tayfun; Onen, Murat; Haensch, Wilfried

2017-01-01

In a previous work we have detailed the requirements for obtaining maximal deep learning performance benefit by implementing fully connected deep neural networks (DNN) in the form of arrays of resistive devices. Here we extend the concept of Resistive Processing Unit (RPU) devices to convolutional neural networks (CNNs). We show how to map the convolutional layers to fully connected RPU arrays such that the parallelism of the hardware can be fully utilized in all three cycles of the backpropagation algorithm. We find that the noise and bound limitations imposed by the analog nature of the computations performed on the arrays significantly affect the training accuracy of the CNNs. Noise and bound management techniques are presented that mitigate these problems without introducing any additional complexity in the analog circuits and that can be addressed by the digital circuits. In addition, we discuss digitally programmable update management and device variability reduction techniques that can be used selectively for some of the layers in a CNN. We show that a combination of all those techniques enables a successful application of the RPU concept for training CNNs. The techniques discussed here are more general and can be applied beyond CNN architectures and therefore enables applicability of the RPU approach to a large class of neural network architectures.

Multi-static networked 3D ladar for surveillance and access control

NASA Astrophysics Data System (ADS)

Wang, Y.; Ogirala, S. S. R.; Hu, B.; Le, Han Q.

2007-04-01

A theoretical design and simulation of a 3D ladar system concept for surveillance, intrusion detection, and access control is described. It is a non-conventional system architecture that consists of: i) multi-static configuration with an arbitrarily scalable number of transmitters (Tx's) and receivers (Rx's) that form an optical wireless code-division-multiple-access (CDMA) network, and ii) flexible system architecture with modular plug-and-play components that can be deployed for any facility with arbitrary topology. Affordability is a driving consideration; and a key feature for low cost is an asymmetric use of many inexpensive Rx's in conjunction with fewer Tx's, which are generally more expensive. The Rx's are spatially distributed close to the surveyed area for large coverage, and capable of receiving signals from multiple Tx's with moderate laser power. The system produces sensing information that scales as NxM, where N, M are the number of Tx's and Rx's, as opposed to linear scaling ~N in non-network system. Also, for target positioning, besides laser pointing direction and time-of-flight, the algorithm includes multiple point-of-view image fusion and triangulation for enhanced accuracy, which is not applicable to non-networked monostatic ladars. Simulation and scaled model experiments on some aspects of this concept are discussed.

An introduction to deep learning on biological sequence data: examples and solutions.

PubMed

Jurtz, Vanessa Isabell; Johansen, Alexander Rosenberg; Nielsen, Morten; Almagro Armenteros, Jose Juan; Nielsen, Henrik; Sønderby, Casper Kaae; Winther, Ole; Sønderby, Søren Kaae

2017-11-15

Deep neural network architectures such as convolutional and long short-term memory networks have become increasingly popular as machine learning tools during the recent years. The availability of greater computational resources, more data, new algorithms for training deep models and easy to use libraries for implementation and training of neural networks are the drivers of this development. The use of deep learning has been especially successful in image recognition; and the development of tools, applications and code examples are in most cases centered within this field rather than within biology. Here, we aim to further the development of deep learning methods within biology by providing application examples and ready to apply and adapt code templates. Given such examples, we illustrate how architectures consisting of convolutional and long short-term memory neural networks can relatively easily be designed and trained to state-of-the-art performance on three biological sequence problems: prediction of subcellular localization, protein secondary structure and the binding of peptides to MHC Class II molecules. All implementations and datasets are available online to the scientific community at https://github.com/vanessajurtz/lasagne4bio. skaaesonderby@gmail.com. Supplementary data are available at Bioinformatics online. © The Author (2017). Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com

Applications of Wireless Sensor Networks in Marine Environment Monitoring: A Survey

PubMed Central

Xu, Guobao; Shen, Weiming; Wang, Xianbin

2014-01-01

With the rapid development of society and the economy, an increasing number of human activities have gradually destroyed the marine environment. Marine environment monitoring is a vital problem and has increasingly attracted a great deal of research and development attention. During the past decade, various marine environment monitoring systems have been developed. The traditional marine environment monitoring system using an oceanographic research vessel is expensive and time-consuming and has a low resolution both in time and space. Wireless Sensor Networks (WSNs) have recently been considered as potentially promising alternatives for monitoring marine environments since they have a number of advantages such as unmanned operation, easy deployment, real-time monitoring, and relatively low cost. This paper provides a comprehensive review of the state-of-the-art technologies in the field of marine environment monitoring using wireless sensor networks. It first describes application areas, a common architecture of WSN-based oceanographic monitoring systems, a general architecture of an oceanographic sensor node, sensing parameters and sensors, and wireless communication technologies. Then, it presents a detailed review of some related projects, systems, techniques, approaches and algorithms. It also discusses challenges and opportunities in the research, development, and deployment of wireless sensor networks for marine environment monitoring. PMID:25215942

Parallel Architectures and Parallel Algorithms for Integrated Vision Systems. Ph.D. Thesis

NASA Technical Reports Server (NTRS)

Choudhary, Alok Nidhi

1989-01-01

Computer vision is regarded as one of the most complex and computationally intensive problems. An integrated vision system (IVS) is a system that uses vision algorithms from all levels of processing to perform for a high level application (e.g., object recognition). An IVS normally involves algorithms from low level, intermediate level, and high level vision. Designing parallel architectures for vision systems is of tremendous interest to researchers. Several issues are addressed in parallel architectures and parallel algorithms for integrated vision systems.

Self-Organizing Maps-based ocean currents forecasting system.

PubMed

Vilibić, Ivica; Šepić, Jadranka; Mihanović, Hrvoje; Kalinić, Hrvoje; Cosoli, Simone; Janeković, Ivica; Žagar, Nedjeljka; Jesenko, Blaž; Tudor, Martina; Dadić, Vlado; Ivanković, Damir

2016-03-16

An ocean surface currents forecasting system, based on a Self-Organizing Maps (SOM) neural network algorithm, high-frequency (HF) ocean radar measurements and numerical weather prediction (NWP) products, has been developed for a coastal area of the northern Adriatic and compared with operational ROMS-derived surface currents. The two systems differ significantly in architecture and algorithms, being based on either unsupervised learning techniques or ocean physics. To compare performance of the two methods, their forecasting skills were tested on independent datasets. The SOM-based forecasting system has a slightly better forecasting skill, especially during strong wind conditions, with potential for further improvement when data sets of higher quality and longer duration are used for training.

The Weather Forecast Using Data Mining Research Based on Cloud Computing.

NASA Astrophysics Data System (ADS)

Wang, ZhanJie; Mazharul Mujib, A. B. M.

2017-10-01

Weather forecasting has been an important application in meteorology and one of the most scientifically and technologically challenging problem around the world. In my study, we have analyzed the use of data mining techniques in forecasting weather. This paper proposes a modern method to develop a service oriented architecture for the weather information systems which forecast weather using these data mining techniques. This can be carried out by using Artificial Neural Network and Decision tree Algorithms and meteorological data collected in Specific time. Algorithm has presented the best results to generate classification rules for the mean weather variables. The results showed that these data mining techniques can be enough for weather forecasting.

Self-Organizing Maps-based ocean currents forecasting system

PubMed Central

Vilibić, Ivica; Šepić, Jadranka; Mihanović, Hrvoje; Kalinić, Hrvoje; Cosoli, Simone; Janeković, Ivica; Žagar, Nedjeljka; Jesenko, Blaž; Tudor, Martina; Dadić, Vlado; Ivanković, Damir

2016-01-01

An ocean surface currents forecasting system, based on a Self-Organizing Maps (SOM) neural network algorithm, high-frequency (HF) ocean radar measurements and numerical weather prediction (NWP) products, has been developed for a coastal area of the northern Adriatic and compared with operational ROMS-derived surface currents. The two systems differ significantly in architecture and algorithms, being based on either unsupervised learning techniques or ocean physics. To compare performance of the two methods, their forecasting skills were tested on independent datasets. The SOM-based forecasting system has a slightly better forecasting skill, especially during strong wind conditions, with potential for further improvement when data sets of higher quality and longer duration are used for training. PMID:26979129

Artificial neural network intelligent method for prediction

NASA Astrophysics Data System (ADS)

Trifonov, Roumen; Yoshinov, Radoslav; Pavlova, Galya; Tsochev, Georgi

2017-09-01

Accounting and financial classification and prediction problems are high challenge and researchers use different methods to solve them. Methods and instruments for short time prediction of financial operations using artificial neural network are considered. The methods, used for prediction of financial data as well as the developed forecasting system with neural network are described in the paper. The architecture of a neural network used four different technical indicators, which are based on the raw data and the current day of the week is presented. The network developed is used for forecasting movement of stock prices one day ahead and consists of an input layer, one hidden layer and an output layer. The training method is algorithm with back propagation of the error. The main advantage of the developed system is self-determination of the optimal topology of neural network, due to which it becomes flexible and more precise The proposed system with neural network is universal and can be applied to various financial instruments using only basic technical indicators as input data.

Analysis of power management and system latency in wireless sensor networks

NASA Astrophysics Data System (ADS)

Oswald, Matthew T.; Rohwer, Judd A.; Forman, Michael A.

2004-08-01

Successful power management in a wireless sensor network requires optimization of the protocols which affect energy-consumption on each node and the aggregate effects across the larger network. System optimization for a given deployment scenario requires an analysis and trade off of desired node and network features with their associated costs. The sleep protocol for an energy-efficient wireless sensor network for event detection, target classification, and target tracking developed at Sandia National Laboratories is presented. The dynamic source routing (DSR) algorithm is chosen to reduce network maintenance overhead, while providing a self-configuring and self-healing network architecture. A method for determining the optimal sleep time is developed and presented, providing reference data which spans several orders of magnitude. Message timing diagrams show, that a node in a five-node cluster, employing an optimal cyclic single-radio sleep protocol, consumes 3% more energy and incurs a 16-s increase latency than nodes employing the more complex dual-radio STEM protocol.

Optimized hardware framework of MLP with random hidden layers for classification applications

NASA Astrophysics Data System (ADS)

Zyarah, Abdullah M.; Ramesh, Abhishek; Merkel, Cory; Kudithipudi, Dhireesha

2016-05-01

Multilayer Perceptron Networks with random hidden layers are very efficient at automatic feature extraction and offer significant performance improvements in the training process. They essentially employ large collection of fixed, random features, and are expedient for form-factor constrained embedded platforms. In this work, a reconfigurable and scalable architecture is proposed for the MLPs with random hidden layers with a customized building block based on CORDIC algorithm. The proposed architecture also exploits fixed point operations for area efficiency. The design is validated for classification on two different datasets. An accuracy of ~ 90% for MNIST dataset and 75% for gender classification on LFW dataset was observed. The hardware has 299 speed-up over the corresponding software realization.

Transmission and visualization of large geographical maps

NASA Astrophysics Data System (ADS)

Zhang, Liqiang; Zhang, Liang; Ren, Yingchao; Guo, Zhifeng

Transmission and visualization of large geographical maps have become a challenging research issue in GIS applications. This paper presents an efficient and robust way to simplify large geographical maps using frame buffers and Voronoi diagrams. The topological relationships are kept during the simplification by removing the Voronoi diagram's self-overlapped regions. With the simplified vector maps, we establish different levels of detail (LOD) models of these maps. Then we introduce a client/server architecture which integrates our out-of-core algorithm, progressive transmission and rendering scheme based on computer graphics hardware. The architecture allows the viewers to view different regions interactively at different LODs on the network. Experimental results show that our proposed scheme provides an effective way for powerful transmission and manipulation of large maps.

Anticipatory Cognitive Systems: a Theoretical Model

NASA Astrophysics Data System (ADS)

Terenzi, Graziano

This paper deals with the problem of understanding anticipation in biological and cognitive systems. It is argued that a physical theory can be considered as biologically plausible only if it incorporates the ability to describe systems which exhibit anticipatory behaviors. The paper introduces a cognitive level description of anticipation and provides a simple theoretical characterization of anticipatory systems on this level. Specifically, a simple model of a formal anticipatory neuron and a model (i.e. the τ-mirror architecture) of an anticipatory neural network which is based on the former are introduced and discussed. The basic feature of this architecture is that a part of the network learns to represent the behavior of the other part over time, thus constructing an implicit model of its own functioning. As a consequence, the network is capable of self-representation; anticipation, on a oscopic level, is nothing but a consequence of anticipation on a microscopic level. Some learning algorithms are also discussed together with related experimental tasks and possible integrations. The outcome of the paper is a formal characterization of anticipation in cognitive systems which aims at being incorporated in a comprehensive and more general physical theory.

The GOES-R Product Generation Architecture

NASA Astrophysics Data System (ADS)

Dittberner, G. J.; Kalluri, S.; Hansen, D.; Weiner, A.; Tarpley, A.; Marley, S.

2011-12-01

The GOES-R system will substantially improve users' ability to succeed in their work by providing data with significantly enhanced instruments, higher resolution, much shorter relook times, and an increased number and diversity of products. The Product Generation architecture is designed to provide the computer and memory resources necessary to achieve the necessary latency and availability for these products. Over time, new and updated algorithms are expected to be added and old ones removed as science advances and new products are developed. The GOES-R GS architecture is being planned to maintain functionality so that when such changes are implemented, operational product generation will continue without interruption. The primary parts of the PG infrastructure are the Service Based Architecture (SBA) and the Data Fabric (DF). SBA is the middleware that encapsulates and manages science algorithms that generate products. It is divided into three parts, the Executive, which manages and configures the algorithm as a service, the Dispatcher, which provides data to the algorithm, and the Strategy, which determines when the algorithm can execute with the available data. SBA is a distributed architecture, with services connected to each other over a compute grid and is highly scalable. This plug-and-play architecture allows algorithms to be added, removed, or updated without affecting any other services or software currently running and producing data. Algorithms require product data from other algorithms, so a scalable and reliable messaging is necessary. The SBA uses the DF to provide this data communication layer between algorithms. The DF provides an abstract interface over a distributed and persistent multi-layered storage system (e.g., memory based caching above disk-based storage) and an event management system that allows event-driven algorithm services to know when instrument data are available and where they reside. Together, the SBA and the DF provide a flexible, high performance architecture that can meet the needs of product processing now and as they grow in the future.

GPU-completeness: theory and implications

NASA Astrophysics Data System (ADS)

Lin, I.-Jong

2011-01-01

This paper formalizes a major insight into a class of algorithms that relate parallelism and performance. The purpose of this paper is to define a class of algorithms that trades off parallelism for quality of result (e.g. visual quality, compression rate), and we propose a similar method for algorithmic classification based on NP-Completeness techniques, applied toward parallel acceleration. We will define this class of algorithm as "GPU-Complete" and will postulate the necessary properties of the algorithms for admission into this class. We will also formally relate his algorithmic space and imaging algorithms space. This concept is based upon our experience in the print production area where GPUs (Graphic Processing Units) have shown a substantial cost/performance advantage within the context of HPdelivered enterprise services and commercial printing infrastructure. While CPUs and GPUs are converging in their underlying hardware and functional blocks, their system behaviors are clearly distinct in many ways: memory system design, programming paradigms, and massively parallel SIMD architecture. There are applications that are clearly suited to each architecture: for CPU: language compilation, word processing, operating systems, and other applications that are highly sequential in nature; for GPU: video rendering, particle simulation, pixel color conversion, and other problems clearly amenable to massive parallelization. While GPUs establishing themselves as a second, distinct computing architecture from CPUs, their end-to-end system cost/performance advantage in certain parts of computation inform the structure of algorithms and their efficient parallel implementations. While GPUs are merely one type of architecture for parallelization, we show that their introduction into the design space of printing systems demonstrate the trade-offs against competing multi-core, FPGA, and ASIC architectures. While each architecture has its own optimal application, we believe that the selection of architecture can be defined in terms of properties of GPU-Completeness. For a welldefined subset of algorithms, GPU-Completeness is intended to connect the parallelism, algorithms and efficient architectures into a unified framework to show that multiple layers of parallel implementation are guided by the same underlying trade-off.

Strategies for concurrent processing of complex algorithms in data driven architectures

NASA Technical Reports Server (NTRS)

Stoughton, John W.; Mielke, Roland R.

1988-01-01

Research directed at developing a graph theoretical model for describing data and control flow associated with the execution of large grained algorithms in a special distributed computer environment is presented. This model is identified by the acronym ATAMM which represents Algorithms To Architecture Mapping Model. The purpose of such a model is to provide a basis for establishing rules for relating an algorithm to its execution in a multiprocessor environment. Specifications derived from the model lead directly to the description of a data flow architecture which is a consequence of the inherent behavior of the data and control flow described by the model. The purpose of the ATAMM based architecture is to provide an analytical basis for performance evaluation. The ATAMM model and architecture specifications are demonstrated on a prototype system for concept validation.

Intrinsic and task-evoked network architectures of the human brain

PubMed Central

Cole, Michael W.; Bassett, Danielle S.; Power, Jonathan D.; Braver, Todd S.; Petersen, Steven E.

2014-01-01

Summary Many functional network properties of the human brain have been identified during rest and task states, yet it remains unclear how the two relate. We identified a whole-brain network architecture present across dozens of task states that was highly similar to the resting-state network architecture. The most frequent functional connectivity strengths across tasks closely matched the strengths observed at rest, suggesting this is an “intrinsic”, standard architecture of functional brain organization. Further, a set of small but consistent changes common across tasks suggests the existence of a task-general network architecture distinguishing task states from rest. These results indicate the brain’s functional network architecture during task performance is shaped primarily by an intrinsic network architecture that is also present during rest, and secondarily by evoked task-general and task-specific network changes. This establishes a strong relationship between resting-state functional connectivity and task-evoked functional connectivity – areas of neuroscientific inquiry typically considered separately. PMID:24991964

A research on the application of software defined networking in satellite network architecture

NASA Astrophysics Data System (ADS)

Song, Huan; Chen, Jinqiang; Cao, Suzhi; Cui, Dandan; Li, Tong; Su, Yuxing

2017-10-01

Software defined network is a new type of network architecture, which decouples control plane and data plane of traditional network, has the feature of flexible configurations and is a direction of the next generation terrestrial Internet development. Satellite network is an important part of the space-ground integrated information network, while the traditional satellite network has the disadvantages of difficult network topology maintenance and slow configuration. The application of SDN technology in satellite network can solve these problems that traditional satellite network faces. At present, the research on the application of SDN technology in satellite network is still in the stage of preliminary study. In this paper, we start with introducing the SDN technology and satellite network architecture. Then we mainly introduce software defined satellite network architecture, as well as the comparison of different software defined satellite network architecture and satellite network virtualization. Finally, the present research status and development trend of SDN technology in satellite network are analyzed.

Analysis of multigrid methods on massively parallel computers: Architectural implications

NASA Technical Reports Server (NTRS)

Matheson, Lesley R.; Tarjan, Robert E.

1993-01-01

We study the potential performance of multigrid algorithms running on massively parallel computers with the intent of discovering whether presently envisioned machines will provide an efficient platform for such algorithms. We consider the domain parallel version of the standard V cycle algorithm on model problems, discretized using finite difference techniques in two and three dimensions on block structured grids of size 10(exp 6) and 10(exp 9), respectively. Our models of parallel computation were developed to reflect the computing characteristics of the current generation of massively parallel multicomputers. These models are based on an interconnection network of 256 to 16,384 message passing, 'workstation size' processors executing in an SPMD mode. The first model accomplishes interprocessor communications through a multistage permutation network. The communication cost is a logarithmic function which is similar to the costs in a variety of different topologies. The second model allows single stage communication costs only. Both models were designed with information provided by machine developers and utilize implementation derived parameters. With the medium grain parallelism of the current generation and the high fixed cost of an interprocessor communication, our analysis suggests an efficient implementation requires the machine to support the efficient transmission of long messages, (up to 1000 words) or the high initiation cost of a communication must be significantly reduced through an alternative optimization technique. Furthermore, with variable length message capability, our analysis suggests the low diameter multistage networks provide little or no advantage over a simple single stage communications network.

Design of robust flow processing networks with time-programmed responses

NASA Astrophysics Data System (ADS)

Kaluza, P.; Mikhailov, A. S.

2012-04-01

Can artificially designed networks reach the levels of robustness against local damage which are comparable with those of the biochemical networks of a living cell? We consider a simple model where the flow applied to an input node propagates through the network and arrives at different times to the output nodes, thus generating a pattern of coordinated responses. By using evolutionary optimization algorithms, functional networks - with required time-programmed responses - were constructed. Then, continuing the evolution, such networks were additionally optimized for robustness against deletion of individual nodes or links. In this manner, large ensembles of functional networks with different kinds of robustness were obtained, making statistical investigations and comparison of their structural properties possible. We have found that, generally, different architectures are needed for various kinds of robustness. The differences are statistically revealed, for example, in the Laplacian spectra of the respective graphs. On the other hand, motif distributions of robust networks do not differ from those of the merely functional networks; they are found to belong to the first Alon superfamily, the same as that of the gene transcription networks of single-cell organisms.

Algorithm architecture co-design for ultra low-power image sensor

NASA Astrophysics Data System (ADS)

Laforest, T.; Dupret, A.; Verdant, A.; Lattard, D.; Villard, P.

2012-03-01

In a context of embedded video surveillance, stand alone leftbehind image sensors are used to detect events with high level of confidence, but also with a very low power consumption. Using a steady camera, motion detection algorithms based on background estimation to find regions in movement are simple to implement and computationally efficient. To reduce power consumption, the background is estimated using a down sampled image formed of macropixels. In order to extend the class of moving objects to be detected, we propose an original mixed mode architecture developed thanks to an algorithm architecture co-design methodology. This programmable architecture is composed of a vector of SIMD processors. A basic RISC architecture was optimized in order to implement motion detection algorithms with a dedicated set of 42 instructions. Definition of delta modulation as a calculation primitive has allowed to implement algorithms in a very compact way. Thereby, a 1920x1080@25fps CMOS image sensor performing integrated motion detection is proposed with a power estimation of 1.8 mW.

On the Deduction of Galactic Abundances with Evolutionary Neural Networks

NASA Astrophysics Data System (ADS)

Taylor, M.; Diaz, A. I.

2007-12-01

A growing number of indicators are now being used with some confidence to measure the metallicity(Z) of photoionisation regions in planetary nebulae, galactic HII regions(GHIIRs), extra-galactic HII regions(EGHIIRs) and HII galaxies(HIIGs). However, a universal indicator valid also at high metallicities has yet to be found. Here, we report on a new artificial intelligence-based approach to determine metallicity indicators that shows promise for the provision of improved empirical fits. The method hinges on the application of an evolutionary neural network to observational emission line data. The network's DNA, encoded in its architecture, weights and neuron transfer functions, is evolved using a genetic algorithm. Furthermore, selection, operating on a set of 10 distinct neuron transfer functions, means that the empirical relation encoded in the network solution architecture is in functional rather than numerical form. Thus the network solutions provide an equation for the metallicity in terms of line ratios without a priori assumptions. Tapping into the mathematical power offered by this approach, we applied the network to detailed observations of both nebula and auroral emission lines from 0.33μ m-1μ m for a sample of 96 HII-type regions and we were able to obtain an empirical relation between Z and S_{23} with a dispersion of only 0.16 dex. We show how the method can be used to identify new diagnostics as well as the nonlinear relationship supposed to exist between the metallicity Z, ionisation parameter U and effective (or equivalent) temperature T*.

Petri net model for analysis of concurrently processed complex algorithms

NASA Technical Reports Server (NTRS)

Stoughton, John W.; Mielke, Roland R.

1986-01-01

This paper presents a Petri-net model suitable for analyzing the concurrent processing of computationally complex algorithms. The decomposed operations are to be processed in a multiple processor, data driven architecture. Of particular interest is the application of the model to both the description of the data/control flow of a particular algorithm, and to the general specification of the data driven architecture. A candidate architecture is also presented.

Framework for waveband switching in multigranular optical networks: part I-multigranular cross-connect architectures [Invited

NASA Astrophysics Data System (ADS)

Cao, Xiaojun; Anand, Vishal; Qiao, Chunming

2006-12-01

Optical networks using wavelength-division multiplexing (WDM) are the foremost solution to the ever-increasing traffic in the Internet backbone. Rapid advances in WDM technology will enable each fiber to carry hundreds or even a thousand wavelengths (using dense-WDM, or DWDM, and ultra-DWDM) of traffic. This, coupled with worldwide fiber deployment, will bring about a tremendous increase in the size of the optical cross-connects, i.e., the number of ports of the wavelength switching elements. Waveband switching (WBS), wherein wavelengths are grouped into bands and switched as a single entity, can reduce the cost and control complexity of switching nodes by minimizing the port count. This paper presents a detailed study on recent advances and open research issues in WBS networks. In this study, we investigate in detail the architecture for various WBS cross-connects and compare them in terms of the number of ports and complexity and also in terms of how flexible they are in adjusting to dynamic traffic. We outline various techniques for grouping wavelengths into bands for the purpose of WBS and show how traditional wavelength routing is different from waveband routing and why techniques developed for wavelength-routed networks (WRNs) cannot be simply applied to WBS networks. We also outline how traffic grooming of subwavelength traffic can be done in WBS networks. In part II of this study [Cao , submitted to J. Opt. Netw.], we study the effect of wavelength conversion on the performance of WBS networks with reconfigurable MG-OXCs. We present an algorithm for waveband grouping in wavelength-convertible networks and evaluate its performance. We also investigate issues related to survivability in WBS networks and show how waveband and wavelength conversion can be used to recover from failures in WBS networks.

Distributed Prognostics and Health Management with a Wireless Network Architecture

NASA Technical Reports Server (NTRS)

Goebel, Kai; Saha, Sankalita; Sha, Bhaskar

2013-01-01

A heterogeneous set of system components monitored by a varied suite of sensors and a particle-filtering (PF) framework, with the power and the flexibility to adapt to the different diagnostic and prognostic needs, has been developed. Both the diagnostic and prognostic tasks are formulated as a particle-filtering problem in order to explicitly represent and manage uncertainties in state estimation and remaining life estimation. Current state-of-the-art prognostic health management (PHM) systems are mostly centralized in nature, where all the processing is reliant on a single processor. This can lead to a loss in functionality in case of a crash of the central processor or monitor. Furthermore, with increases in the volume of sensor data as well as the complexity of algorithms, traditional centralized systems become for a number of reasons somewhat ungainly for successful deployment, and efficient distributed architectures can be more beneficial. The distributed health management architecture is comprised of a network of smart sensor devices. These devices monitor the health of various subsystems or modules. They perform diagnostics operations and trigger prognostics operations based on user-defined thresholds and rules. The sensor devices, called computing elements (CEs), consist of a sensor, or set of sensors, and a communication device (i.e., a wireless transceiver beside an embedded processing element). The CE runs in either a diagnostic or prognostic operating mode. The diagnostic mode is the default mode where a CE monitors a given subsystem or component through a low-weight diagnostic algorithm. If a CE detects a critical condition during monitoring, it raises a flag. Depending on availability of resources, a networked local cluster of CEs is formed that then carries out prognostics and fault mitigation by efficient distribution of the tasks. It should be noted that the CEs are expected not to suspend their previous tasks in the prognostic mode. When the prognostics task is over, and after appropriate actions have been taken, all CEs return to their original default configuration. Wireless technology-based implementation would ensure more flexibility in terms of sensor placement. It would also allow more sensors to be deployed because the overhead related to weights of wired systems is not present. Distributed architectures are furthermore generally robust with regard to recovery from node failures.

Multitarget-multisensor management for decentralized sensor networks

NASA Astrophysics Data System (ADS)

Tharmarasa, R.; Kirubarajan, T.; Sinha, A.; Hernandez, M. L.

2006-05-01

In this paper, we consider the problem of sensor resource management in decentralized tracking systems. Due to the availability of cheap sensors, it is possible to use a large number of sensors and a few fusion centers (FCs) to monitor a large surveillance region. Even though a large number of sensors are available, due to frequency, power and other physical limitations, only a few of them can be active at any one time. The problem is then to select sensor subsets that should be used by each FC at each sampling time in order to optimize the tracking performance subject to their operational constraints. In a recent paper, we proposed an algorithm to handle the above issues for joint detection and tracking, without using simplistic clustering techniques that are standard in the literature. However, in that paper, a hierarchical architecture with feedback at every sampling time was considered, and the sensor management was performed only at a central fusion center (CFC). However, in general, it is not possible to communicate with the CFC at every sampling time, and in many cases there may not even be a CFC. Sometimes, communication between CFC and local fusion centers might fail as well. Therefore performing sensor management only at the CFC is not viable in most networks. In this paper, we consider an architecture in which there is no CFC, each FC communicates only with the neighboring FCs, and communications are restricted. In this case, each FC has to decide which sensors are to be used by itself at each measurement time step. We propose an efficient algorithm to handle the above problem in real time. Simulation results illustrating the performance of the proposed algorithm are also presented.

MASM: a market architecture for sensor management in distributed sensor networks

NASA Astrophysics Data System (ADS)

Viswanath, Avasarala; Mullen, Tracy; Hall, David; Garga, Amulya

2005-03-01

Rapid developments in sensor technology and its applications have energized research efforts towards devising a firm theoretical foundation for sensor management. Ubiquitous sensing, wide bandwidth communications and distributed processing provide both opportunities and challenges for sensor and process control and optimization. Traditional optimization techniques do not have the ability to simultaneously consider the wildly non-commensurate measures involved in sensor management in a single optimization routine. Market-oriented programming provides a valuable and principled paradigm to designing systems to solve this dynamic and distributed resource allocation problem. We have modeled the sensor management scenario as a competitive market, wherein the sensor manager holds a combinatorial auction to sell the various items produced by the sensors and the communication channels. However, standard auction mechanisms have been found not to be directly applicable to the sensor management domain. For this purpose, we have developed a specialized market architecture MASM (Market architecture for Sensor Management). In MASM, the mission manager is responsible for deciding task allocations to the consumers and their corresponding budgets and the sensor manager is responsible for resource allocation to the various consumers. In addition to having a modified combinatorial winner determination algorithm, MASM has specialized sensor network modules that address commensurability issues between consumers and producers in the sensor network domain. A preliminary multi-sensor, multi-target simulation environment has been implemented to test the performance of the proposed system. MASM outperformed the information theoretic sensor manager in meeting the mission objectives in the simulation experiments.

A Low Cost VLSI Architecture for Spike Sorting Based on Feature Extraction with Peak Search.

PubMed

Chang, Yuan-Jyun; Hwang, Wen-Jyi; Chen, Chih-Chang

2016-12-07

The goal of this paper is to present a novel VLSI architecture for spike sorting with high classification accuracy, low area costs and low power consumption. A novel feature extraction algorithm with low computational complexities is proposed for the design of the architecture. In the feature extraction algorithm, a spike is separated into two portions based on its peak value. The area of each portion is then used as a feature. The algorithm is simple to implement and less susceptible to noise interference. Based on the algorithm, a novel architecture capable of identifying peak values and computing spike areas concurrently is proposed. To further accelerate the computation, a spike can be divided into a number of segments for the local feature computation. The local features are subsequently merged with the global ones by a simple hardware circuit. The architecture can also be easily operated in conjunction with the circuits for commonly-used spike detection algorithms, such as the Non-linear Energy Operator (NEO). The architecture has been implemented by an Application-Specific Integrated Circuit (ASIC) with 90-nm technology. Comparisons to the existing works show that the proposed architecture is well suited for real-time multi-channel spike detection and feature extraction requiring low hardware area costs, low power consumption and high classification accuracy.

A parallel computing engine for a class of time critical processes.

PubMed

Nabhan, T M; Zomaya, A Y

1997-01-01

This paper focuses on the efficient parallel implementation of systems of numerically intensive nature over loosely coupled multiprocessor architectures. These analytical models are of significant importance to many real-time systems that have to meet severe time constants. A parallel computing engine (PCE) has been developed in this work for the efficient simplification and the near optimal scheduling of numerical models over the different cooperating processors of the parallel computer. First, the analytical system is efficiently coded in its general form. The model is then simplified by using any available information (e.g., constant parameters). A task graph representing the interconnections among the different components (or equations) is generated. The graph can then be compressed to control the computation/communication requirements. The task scheduler employs a graph-based iterative scheme, based on the simulated annealing algorithm, to map the vertices of the task graph onto a Multiple-Instruction-stream Multiple-Data-stream (MIMD) type of architecture. The algorithm uses a nonanalytical cost function that properly considers the computation capability of the processors, the network topology, the communication time, and congestion possibilities. Moreover, the proposed technique is simple, flexible, and computationally viable. The efficiency of the algorithm is demonstrated by two case studies with good results.

Hardware architecture design of image restoration based on time-frequency domain computation

NASA Astrophysics Data System (ADS)

Wen, Bo; Zhang, Jing; Jiao, Zipeng

2013-10-01

The image restoration algorithms based on time-frequency domain computation is high maturity and applied widely in engineering. To solve the high-speed implementation of these algorithms, the TFDC hardware architecture is proposed. Firstly, the main module is designed, by analyzing the common processing and numerical calculation. Then, to improve the commonality, the iteration control module is planed for iterative algorithms. In addition, to reduce the computational cost and memory requirements, the necessary optimizations are suggested for the time-consuming module, which include two-dimensional FFT/IFFT and the plural calculation. Eventually, the TFDC hardware architecture is adopted for hardware design of real-time image restoration system. The result proves that, the TFDC hardware architecture and its optimizations can be applied to image restoration algorithms based on TFDC, with good algorithm commonality, hardware realizability and high efficiency.

Parallel Algorithms for Monte Carlo Particle Transport Simulation on Exascale Computing Architectures

NASA Astrophysics Data System (ADS)

Romano, Paul Kollath

Monte Carlo particle transport methods are being considered as a viable option for high-fidelity simulation of nuclear reactors. While Monte Carlo methods offer several potential advantages over deterministic methods, there are a number of algorithmic shortcomings that would prevent their immediate adoption for full-core analyses. In this thesis, algorithms are proposed both to ameliorate the degradation in parallel efficiency typically observed for large numbers of processors and to offer a means of decomposing large tally data that will be needed for reactor analysis. A nearest-neighbor fission bank algorithm was proposed and subsequently implemented in the OpenMC Monte Carlo code. A theoretical analysis of the communication pattern shows that the expected cost is O( N ) whereas traditional fission bank algorithms are O(N) at best. The algorithm was tested on two supercomputers, the Intrepid Blue Gene/P and the Titan Cray XK7, and demonstrated nearly linear parallel scaling up to 163,840 processor cores on a full-core benchmark problem. An algorithm for reducing network communication arising from tally reduction was analyzed and implemented in OpenMC. The proposed algorithm groups only particle histories on a single processor into batches for tally purposes---in doing so it prevents all network communication for tallies until the very end of the simulation. The algorithm was tested, again on a full-core benchmark, and shown to reduce network communication substantially. A model was developed to predict the impact of load imbalances on the performance of domain decomposed simulations. The analysis demonstrated that load imbalances in domain decomposed simulations arise from two distinct phenomena: non-uniform particle densities and non-uniform spatial leakage. The dominant performance penalty for domain decomposition was shown to come from these physical effects rather than insufficient network bandwidth or high latency. The model predictions were verified with measured data from simulations in OpenMC on a full-core benchmark problem. Finally, a novel algorithm for decomposing large tally data was proposed, analyzed, and implemented/tested in OpenMC. The algorithm relies on disjoint sets of compute processes and tally servers. The analysis showed that for a range of parameters relevant to LWR analysis, the tally server algorithm should perform with minimal overhead. Tests were performed on Intrepid and Titan and demonstrated that the algorithm did indeed perform well over a wide range of parameters. (Copies available exclusively from MIT Libraries, libraries.mit.edu/docs - docs mit.edu)

A Power Planning Algorithm Based on RPL for AMI Wireless Sensor Networks.

PubMed

Miguel, Marcio L F; Jamhour, Edgard; Pellenz, Marcelo E; Penna, Manoel C

2017-03-25

The advanced metering infrastructure (AMI) is an architecture for two-way communication between electric, gas and water meters and city utilities. The AMI network is a wireless sensor network that provides communication for metering devices in the neighborhood area of the smart grid. Recently, the applicability of a routing protocol for low-power and lossy networks (RPL) has been considered in AMI networks. Some studies in the literature have pointed out problems with RPL, including sub-optimal path selection and instability. In this paper, we defend the viewpoint that careful planning of the transmission power in wireless RPL networks can significantly reduce the pointed problems. This paper presents a method for planning the transmission power in order to assure that, after convergence, the size of the parent set of the RPL nodes is as close as possible to a predefined size. Another important feature is that all nodes in the parent set offer connectivity through links of similar quality.

Parallel replica dynamics method for bistable stochastic reaction networks: Simulation and sensitivity analysis

NASA Astrophysics Data System (ADS)

Wang, Ting; Plecháč, Petr

2017-12-01

Stochastic reaction networks that exhibit bistable behavior are common in systems biology, materials science, and catalysis. Sampling of stationary distributions is crucial for understanding and characterizing the long-time dynamics of bistable stochastic dynamical systems. However, simulations are often hindered by the insufficient sampling of rare transitions between the two metastable regions. In this paper, we apply the parallel replica method for a continuous time Markov chain in order to improve sampling of the stationary distribution in bistable stochastic reaction networks. The proposed method uses parallel computing to accelerate the sampling of rare transitions. Furthermore, it can be combined with the path-space information bounds for parametric sensitivity analysis. With the proposed methodology, we study three bistable biological networks: the Schlögl model, the genetic switch network, and the enzymatic futile cycle network. We demonstrate the algorithmic speedup achieved in these numerical benchmarks. More significant acceleration is expected when multi-core or graphics processing unit computer architectures and programming tools such as CUDA are employed.

A Power Planning Algorithm Based on RPL for AMI Wireless Sensor Networks

PubMed Central

Miguel, Marcio L. F.; Jamhour, Edgard; Pellenz, Marcelo E.; Penna, Manoel C.

2017-01-01

The advanced metering infrastructure (AMI) is an architecture for two-way communication between electric, gas and water meters and city utilities. The AMI network is a wireless sensor network that provides communication for metering devices in the neighborhood area of the smart grid. Recently, the applicability of a routing protocol for low-power and lossy networks (RPL) has been considered in AMI networks. Some studies in the literature have pointed out problems with RPL, including sub-optimal path selection and instability. In this paper, we defend the viewpoint that careful planning of the transmission power in wireless RPL networks can significantly reduce the pointed problems. This paper presents a method for planning the transmission power in order to assure that, after convergence, the size of the parent set of the RPL nodes is as close as possible to a predefined size. Another important feature is that all nodes in the parent set offer connectivity through links of similar quality. PMID:28346339

Performance management of multiple access communication networks

NASA Astrophysics Data System (ADS)

Lee, Suk; Ray, Asok

1993-12-01

This paper focuses on conceptual design, development, and implementation of a performance management tool for computer communication networks to serve large-scale integrated systems. The objective is to improve the network performance in handling various types of messages by on-line adjustment of protocol parameters. The techniques of perturbation analysis of Discrete Event Dynamic Systems (DEDS), stochastic approximation (SA), and learning automata have been used in formulating the algorithm of performance management. The efficacy of the performance management tool has been demonstrated on a network testbed. The conceptual design presented in this paper offers a step forward to bridging the gap between management standards and users' demands for efficient network operations since most standards such as ISO (International Standards Organization) and IEEE address only the architecture, services, and interfaces for network management. The proposed concept of performance management can also be used as a general framework to assist design, operation, and management of various DEDS such as computer integrated manufacturing and battlefield C(sup 3) (Command, Control, and Communications).

Speed challenge: a case for hardware implementation in soft-computing

NASA Technical Reports Server (NTRS)

Daud, T.; Stoica, A.; Duong, T.; Keymeulen, D.; Zebulum, R.; Thomas, T.; Thakoor, A.

2000-01-01

For over a decade, JPL has been actively involved in soft computing research on theory, architecture, applications, and electronics hardware. The driving force in all our research activities, in addition to the potential enabling technology promise, has been creation of a niche that imparts orders of magnitude speed advantage by implementation in parallel processing hardware with algorithms made especially suitable for hardware implementation. We review our work on neural networks, fuzzy logic, and evolvable hardware with selected application examples requiring real time response capabilities.

On the application of neural networks to the classification of phase modulated waveforms

NASA Astrophysics Data System (ADS)

Buchenroth, Anthony; Yim, Joong Gon; Nowak, Michael; Chakravarthy, Vasu

2017-04-01

Accurate classification of phase modulated radar waveforms is a well-known problem in spectrum sensing. Identification of such waveforms aids situational awareness enabling radar and communications spectrum sharing. While various feature extraction and engineering approaches have sought to address this problem, the use of a machine learning algorithm that best utilizes these features is becomes foremost. In this effort, a comparison of a standard shallow and a deep learning approach are explored. Experiments provide insights into classifier architecture, training procedure, and performance.

A Fusion Architecture for Tracking a Group of People Using a Distributed Sensor Network

DTIC Science & Technology

2013-07-01

Determining the composition of the group is done using several classifiers. The fusion is done at the UGS level to fuse information from all the modalities to...to classification and counting of the targets. Section III also presents the algorithms for fusion of distributed sensor data at the UGS level and...ultrasonic sensors. Determining the composition of the group is done using several classifiers. The fusion is done at the UGS level to fuse

Performance Evaluation of Parallel Algorithms and Architectures in Concurrent Multiprocessor Systems

DTIC Science & Technology

1988-09-01

HEP and Other Parallel processors, Report no. ANL-83-97, Argonne National Laboratory, Argonne, Ill. 1983. [19] Davidson, G . S. A Practical Paradigm for...IEEE Comp. Soc., 1986. [241 Peir, Jih-kwon, and D. Gajski , "CAMP: A Programming Aide For Multiprocessors," Proc. 1986 ICPP, IEEE Comp. Soc., pp475...482. [251 Pfister, G . F., and V. A. Norton, "Hot Spot Contention and Combining in Multistage Interconnection Networks,"IEEE Trans. Comp., C-34, Oct

Motion camera based on a custom vision sensor and an FPGA architecture

NASA Astrophysics Data System (ADS)

Arias-Estrada, Miguel

1998-09-01

A digital camera for custom focal plane arrays was developed. The camera allows the test and development of analog or mixed-mode arrays for focal plane processing. The camera is used with a custom sensor for motion detection to implement a motion computation system. The custom focal plane sensor detects moving edges at the pixel level using analog VLSI techniques. The sensor communicates motion events using the event-address protocol associated to a temporal reference. In a second stage, a coprocessing architecture based on a field programmable gate array (FPGA) computes the time-of-travel between adjacent pixels. The FPGA allows rapid prototyping and flexible architecture development. Furthermore, the FPGA interfaces the sensor to a compact PC computer which is used for high level control and data communication to the local network. The camera could be used in applications such as self-guided vehicles, mobile robotics and smart surveillance systems. The programmability of the FPGA allows the exploration of further signal processing like spatial edge detection or image segmentation tasks. The article details the motion algorithm, the sensor architecture, the use of the event- address protocol for velocity vector computation and the FPGA architecture used in the motion camera system.

Design and performance evaluation of an OpenFlow-based control plane for software-defined elastic optical networks with direct-detection optical OFDM (DDO-OFDM) transmission.

PubMed

Liu, Lei; Peng, Wei-Ren; Casellas, Ramon; Tsuritani, Takehiro; Morita, Itsuro; Martínez, Ricardo; Muñoz, Raül; Yoo, S J B

2014-01-13

Optical Orthogonal Frequency Division Multiplexing (O-OFDM), which transmits high speed optical signals using multiple spectrally overlapped lower-speed subcarriers, is a promising candidate for supporting future elastic optical networks. In contrast to previous works which focus on Coherent Optical OFDM (CO-OFDM), in this paper, we consider the direct-detection optical OFDM (DDO-OFDM) as the transport technique, which leads to simpler hardware and software realizations, potentially offering a low-cost solution for elastic optical networks, especially in metro networks, and short or medium distance core networks. Based on this network scenario, we design and deploy a software-defined networking (SDN) control plane enabled by extending OpenFlow, detailing the network architecture, the routing and spectrum assignment algorithm, OpenFlow protocol extensions and the experimental validation. To the best of our knowledge, it is the first time that an OpenFlow-based control plane is reported and its performance is quantitatively measured in an elastic optical network with DDO-OFDM transmission.

Shuttle Payload Ground Command and Control: An Experiment Implementation Combustion Module-2 Software Development, STS-107

NASA Technical Reports Server (NTRS)

Carek, David Andrew

2003-01-01

This presentation covers the design of a command and control architecture developed by the author for the Combustion Module-2 microgravity experiment, which flew aboard the STS-107 Shuttle mission, The design was implemented to satisfy a hybrid network that utilized TCP/IP for both the onboard segment and ground segment, with an intermediary unreliable transport for the space to ground segment. With the infusion of Internet networking technologies into Space Shuttle, Space Station, and spacecraft avionics systems, comes the need for robust methodologies for ground command and control. Considerations of high bit error links, and unreliable transport over intermittent links must be considered in such systems. Internet protocols applied to these systems, coupled with the appropriate application layer protections, can provide adequate communication architectures for command and control. However, there are inherent limitations and additional complexities added by the use of Internet protocols that must be considered during the design. This presentation will discuss the rationale for the: framework and protocol algorithms developed by the author. A summary of design considerations, implantation issues, and learned lessons will be will be presented. A summary of mission results using this communications architecture will be presented. Additionally, areas of further needed investigation will be identified.

Network Analysis Reveals Putative Genes Affecting Meat Quality in Angus Cattle.

PubMed

Mateescu, Raluca G; Garrick, Dorian J; Reecy, James M

2017-01-01

Improvements in eating satisfaction will benefit consumers and should increase beef demand which is of interest to the beef industry. Tenderness, juiciness, and flavor are major determinants of the palatability of beef and are often used to reflect eating satisfaction. Carcass qualities are used as indicator traits for meat quality, with higher quality grade carcasses expected to relate to more tender and palatable meat. However, meat quality is a complex concept determined by many component traits making interpretation of genome-wide association studies (GWAS) on any one component challenging to interpret. Recent approaches combining traditional GWAS with gene network interactions theory could be more efficient in dissecting the genetic architecture of complex traits. Phenotypic measures of 23 traits reflecting carcass characteristics, components of meat quality, along with mineral and peptide concentrations were used along with Illumina 54k bovine SNP genotypes to derive an annotated gene network associated with meat quality in 2,110 Angus beef cattle. The efficient mixed model association (EMMAX) approach in combination with a genomic relationship matrix was used to directly estimate the associations between 54k SNP genotypes and each of the 23 component traits. Genomic correlated regions were identified by partial correlations which were further used along with an information theory algorithm to derive gene network clusters. Correlated SNP across 23 component traits were subjected to network scoring and visualization software to identify significant SNP. Significant pathways implicated in the meat quality complex through GO term enrichment analysis included angiogenesis, inflammation, transmembrane transporter activity, and receptor activity. These results suggest that network analysis using partial correlations and annotation of significant SNP can reveal the genetic architecture of complex traits and provide novel information regarding biological mechanisms and genes that lead to complex phenotypes, like meat quality, and the nutritional and healthfulness value of beef. Improvements in genome annotation and knowledge of gene function will contribute to more comprehensive analyses that will advance our ability to dissect the complex architecture of complex traits.

Intelligent control and adaptive systems; Proceedings of the Meeting, Philadelphia, PA, Nov. 7, 8, 1989

NASA Technical Reports Server (NTRS)

Rodriguez, Guillermo (Editor)

1990-01-01

Various papers on intelligent control and adaptive systems are presented. Individual topics addressed include: control architecture for a Mars walking vehicle, representation for error detection and recovery in robot task plans, real-time operating system for robots, execution monitoring of a mobile robot system, statistical mechanics models for motion and force planning, global kinematics for manipulator planning and control, exploration of unknown mechanical assemblies through manipulation, low-level representations for robot vision, harmonic functions for robot path construction, simulation of dual behavior of an autonomous system. Also discussed are: control framework for hand-arm coordination, neural network approach to multivehicle navigation, electronic neural networks for global optimization, neural network for L1 norm linear regression, planning for assembly with robot hands, neural networks in dynamical systems, control design with iterative learning, improved fuzzy process control of spacecraft autonomous rendezvous using a genetic algorithm.

Wireless Multimedia Sensor Networks: Current Trends and Future Directions

PubMed Central

Almalkawi, Islam T.; Zapata, Manel Guerrero; Al-Karaki, Jamal N.; Morillo-Pozo, Julian

2010-01-01

Wireless Multimedia Sensor Networks (WMSNs) have emerged and shifted the focus from the typical scalar wireless sensor networks to networks with multimedia devices that are capable to retrieve video, audio, images, as well as scalar sensor data. WMSNs are able to deliver multimedia content due to the availability of inexpensive CMOS cameras and microphones coupled with the significant progress in distributed signal processing and multimedia source coding techniques. In this paper, we outline the design challenges of WMSNs, give a comprehensive discussion of the proposed architectures, algorithms and protocols for the different layers of the communication protocol stack for WMSNs, and evaluate the existing WMSN hardware and testbeds. The paper will give the reader a clear view of the state of the art at all aspects of this research area, and shed the light on its main current challenges and future trends. We also hope it will foster discussions and new research ideas among its researchers. PMID:22163571

Evolvable rough-block-based neural network and its biomedical application to hypoglycemia detection system.

PubMed

San, Phyo Phyo; Ling, Sai Ho; Nuryani; Nguyen, Hung

2014-08-01

This paper focuses on the hybridization technology using rough sets concepts and neural computing for decision and classification purposes. Based on the rough set properties, the lower region and boundary region are defined to partition the input signal to a consistent (predictable) part and an inconsistent (random) part. In this way, the neural network is designed to deal only with the boundary region, which mainly consists of an inconsistent part of applied input signal causing inaccurate modeling of the data set. Owing to different characteristics of neural network (NN) applications, the same structure of conventional NN might not give the optimal solution. Based on the knowledge of application in this paper, a block-based neural network (BBNN) is selected as a suitable classifier due to its ability to evolve internal structures and adaptability in dynamic environments. This architecture will systematically incorporate the characteristics of application to the structure of hybrid rough-block-based neural network (R-BBNN). A global training algorithm, hybrid particle swarm optimization with wavelet mutation is introduced for parameter optimization of proposed R-BBNN. The performance of the proposed R-BBNN algorithm was evaluated by an application to the field of medical diagnosis using real hypoglycemia episodes in patients with Type 1 diabetes mellitus. The performance of the proposed hybrid system has been compared with some of the existing neural networks. The comparison results indicated that the proposed method has improved classification performance and results in early convergence of the network.

Strategies for concurrent processing of complex algorithms in data driven architectures

NASA Technical Reports Server (NTRS)

Stoughton, John W.; Mielke, Roland R.

1987-01-01

The results of ongoing research directed at developing a graph theoretical model for describing data and control flow associated with the execution of large grained algorithms in a spatial distributed computer environment is presented. This model is identified by the acronym ATAMM (Algorithm/Architecture Mapping Model). The purpose of such a model is to provide a basis for establishing rules for relating an algorithm to its execution in a multiprocessor environment. Specifications derived from the model lead directly to the description of a data flow architecture which is a consequence of the inherent behavior of the data and control flow described by the model. The purpose of the ATAMM based architecture is to optimize computational concurrency in the multiprocessor environment and to provide an analytical basis for performance evaluation. The ATAMM model and architecture specifications are demonstrated on a prototype system for concept validation.

Clustalnet: the joining of Clustal and CORBA.

PubMed

Campagne, F

2000-07-01

Performing sequence alignment operations from a different program than the original sequence alignment code, and/or through a network connection, is often required. Interactive alignment editors and large-scale biological data analysis are common examples where such a flexibility is important. Interoperability between the alignment engine and the client should be obtained regardless of the architectures and programming languages of the server and client. Clustalnet, a Clustal alignment CORBA server is described, which was developed on the basis of Clustalw. This server brings the robustness of the algorithms and implementations of Clustal to a new level of reuse. A Clustalnet server object can be accessed from a program, transparently through the network. We present interfaces to perform the alignment operations and to control these operations via immutable contexts. The interfaces that select the contexts do not depend on the nature of the operation to be performed, making the design modular. The IDL interfaces presented here are not specific to Clustal and can be implemented on top of different sequence alignment algorithm implementations.

A new evolutionary system for evolving artificial neural networks.

PubMed

Yao, X; Liu, Y

1997-01-01

This paper presents a new evolutionary system, i.e., EPNet, for evolving artificial neural networks (ANNs). The evolutionary algorithm used in EPNet is based on Fogel's evolutionary programming (EP). Unlike most previous studies on evolving ANN's, this paper puts its emphasis on evolving ANN's behaviors. Five mutation operators proposed in EPNet reflect such an emphasis on evolving behaviors. Close behavioral links between parents and their offspring are maintained by various mutations, such as partial training and node splitting. EPNet evolves ANN's architectures and connection weights (including biases) simultaneously in order to reduce the noise in fitness evaluation. The parsimony of evolved ANN's is encouraged by preferring node/connection deletion to addition. EPNet has been tested on a number of benchmark problems in machine learning and ANNs, such as the parity problem, the medical diagnosis problems, the Australian credit card assessment problem, and the Mackey-Glass time series prediction problem. The experimental results show that EPNet can produce very compact ANNs with good generalization ability in comparison with other algorithms.

DFT algorithms for bit-serial GaAs array processor architectures

NASA Technical Reports Server (NTRS)

Mcmillan, Gary B.

1988-01-01

Systems and Processes Engineering Corporation (SPEC) has developed an innovative array processor architecture for computing Fourier transforms and other commonly used signal processing algorithms. This architecture is designed to extract the highest possible array performance from state-of-the-art GaAs technology. SPEC's architectural design includes a high performance RISC processor implemented in GaAs, along with a Floating Point Coprocessor and a unique Array Communications Coprocessor, also implemented in GaAs technology. Together, these data processors represent the latest in technology, both from an architectural and implementation viewpoint. SPEC has examined numerous algorithms and parallel processing architectures to determine the optimum array processor architecture. SPEC has developed an array processor architecture with integral communications ability to provide maximum node connectivity. The Array Communications Coprocessor embeds communications operations directly in the core of the processor architecture. A Floating Point Coprocessor architecture has been defined that utilizes Bit-Serial arithmetic units, operating at very high frequency, to perform floating point operations. These Bit-Serial devices reduce the device integration level and complexity to a level compatible with state-of-the-art GaAs device technology.

Contention Modeling for Multithreaded Distributed Shared Memory Machines: The Cray XMT

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

Secchi, Simone; Tumeo, Antonino; Villa, Oreste

Distributed Shared Memory (DSM) machines are a wide class of multi-processor computing systems where a large virtually-shared address space is mapped on a network of physically distributed memories. High memory latency and network contention are two of the main factors that limit performance scaling of such architectures. Modern high-performance computing DSM systems have evolved toward exploitation of massive hardware multi-threading and fine-grained memory hashing to tolerate irregular latencies, avoid network hot-spots and enable high scaling. In order to model the performance of such large-scale machines, parallel simulation has been proved to be a promising approach to achieve good accuracy inmore » reasonable times. One of the most critical factors in solving the simulation speed-accuracy trade-off is network modeling. The Cray XMT is a massively multi-threaded supercomputing architecture that belongs to the DSM class, since it implements a globally-shared address space abstraction on top of a physically distributed memory substrate. In this paper, we discuss the development of a contention-aware network model intended to be integrated in a full-system XMT simulator. We start by measuring the effects of network contention in a 128-processor XMT machine and then investigate the trade-off that exists between simulation accuracy and speed, by comparing three network models which operate at different levels of accuracy. The comparison and model validation is performed by executing a string-matching algorithm on the full-system simulator and on the XMT, using three datasets that generate noticeably different contention patterns.« less

Heterogeneous Spacecraft Networks

NASA Technical Reports Server (NTRS)

Nakamura, Yosuke (Inventor); Faber, Nicolas T. (Inventor); Frost, Chad R. (Inventor); Alena, Richard L. (Inventor)

2018-01-01

The present invention provides a heterogeneous spacecraft network including a network management architecture to facilitate communication between a plurality of operations centers and a plurality of data user communities. The network management architecture includes a plurality of network nodes in communication with the plurality of operations centers. The present invention also provides a method of communication for a heterogeneous spacecraft network. The method includes: transmitting data from a first space segment to a first ground segment; transmitting the data from the first ground segment to a network management architecture; transmitting data from a second space segment to a second ground segment, the second space and ground segments having incompatible communication systems with the first space and ground segments; transmitting the data from the second ground station to the network management architecture; and, transmitting data from the network management architecture to a plurality of data user communities.

Generating a fault-tolerant global clock using high-speed control signals for the MetaNet architecture

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

Ofek, Y.

1994-05-01

This work describes a new technique, based on exchanging control signals between neighboring nodes, for constructing a stable and fault-tolerant global clock in a distributed system with an arbitrary topology. It is shown that it is possible to construct a global clock reference with time step that is much smaller than the propagation delay over the network's links. The synchronization algorithm ensures that the global clock tick' has a stable periodicity, and therefore, it is possible to tolerate failures of links and clocks that operate faster and/or slower than nominally specified, as well as hard failures. The approach taken inmore » this work is to generate a global clock from the ensemble of the local transmission clocks and not to directly synchronize these high-speed clocks. The steady-state algorithm, which generates the global clock, is executed in hardware by the network interface of each node. At the network interface, it is possible to measure accurately the propagation delay between neighboring nodes with a small error or uncertainty and thereby to achieve global synchronization that is proportional to these error measurements. It is shown that the local clock drift (or rate uncertainty) has only a secondary effect on the maximum global clock rate. The synchronization algorithm can tolerate any physical failure. 18 refs.« less

Criteria for Evaluating Alternative Network and Link Layer Protocols for the NASA Constellation Program Communication Architecture

NASA Technical Reports Server (NTRS)

Benbenek, Daniel; Soloff, Jason; Lieb, Erica

2010-01-01

Selecting a communications and network architecture for future manned space flight requires an evaluation of the varying goals and objectives of the program, development of communications and network architecture evaluation criteria, and assessment of critical architecture trades. This paper uses Cx Program proposed exploration activities as a guideline; lunar sortie, outpost, Mars, and flexible path options are described. A set of proposed communications network architecture criteria are proposed and described. They include: interoperability, security, reliability, and ease of automating topology changes. Finally a key set of architecture options are traded including (1) multiplexing data at a common network layer vs. at the data link layer, (2) implementing multiple network layers vs. a single network layer, and (3) the use of a particular network layer protocol, primarily IPv6 vs. Delay Tolerant Networking (DTN). In summary, the protocol options are evaluated against the proposed exploration activities and their relative performance with respect to the criteria are assessed. An architectural approach which includes (a) the capability of multiplexing at both the network layer and the data link layer and (b) a single network layer for operations at each program phase, as these solutions are best suited to respond to the widest array of program needs and meet each of the evaluation criteria.

Compact Interconnection Networks Based on Quantum Dots

NASA Technical Reports Server (NTRS)

Fijany, Amir; Toomarian, Nikzad; Modarress, Katayoon; Spotnitz, Matthew

2003-01-01

Architectures that would exploit the distinct characteristics of quantum-dot cellular automata (QCA) have been proposed for digital communication networks that connect advanced digital computing circuits. In comparison with networks of wires in conventional very-large-scale integrated (VLSI) circuitry, the networks according to the proposed architectures would be more compact. The proposed architectures would make it possible to implement complex interconnection schemes that are required for some advanced parallel-computing algorithms and that are difficult (and in many cases impractical) to implement in VLSI circuitry. The difficulty of implementation in VLSI and the major potential advantage afforded by QCA were described previously in Implementing Permutation Matrices by Use of Quantum Dots (NPO-20801), NASA Tech Briefs, Vol. 25, No. 10 (October 2001), page 42. To recapitulate: Wherever two wires in a conventional VLSI circuit cross each other and are required not to be in electrical contact with each other, there must be a layer of electrical insulation between them. This, in turn, makes it necessary to resort to a noncoplanar and possibly a multilayer design, which can be complex, expensive, and even impractical. As a result, much of the cost of designing VLSI circuits is associated with minimization of data routing and assignment of layers to minimize crossing of wires. Heretofore, these considerations have impeded the development of VLSI circuitry to implement complex, advanced interconnection schemes. On the other hand, with suitable design and under suitable operating conditions, QCA-based signal paths can be allowed to cross each other in the same plane without adverse effect. In principle, this characteristic could be exploited to design compact, coplanar, simple (relative to VLSI) QCA-based networks to implement complex, advanced interconnection schemes. The proposed architectures require two advances in QCA-based circuitry beyond basic QCA-based binary-signal wires described in the cited prior article. One of these advances would be the development of QCA-based wires capable of bidirectional transmission of signals. The other advance would be the development of QCA circuits capable of high-impedance state outputs. The high-impedance states would be utilized along with the 0- and 1-state outputs of QCA.

Phylogenetic convolutional neural networks in metagenomics.

PubMed

Fioravanti, Diego; Giarratano, Ylenia; Maggio, Valerio; Agostinelli, Claudio; Chierici, Marco; Jurman, Giuseppe; Furlanello, Cesare

2018-03-08

Convolutional Neural Networks can be effectively used only when data are endowed with an intrinsic concept of neighbourhood in the input space, as is the case of pixels in images. We introduce here Ph-CNN, a novel deep learning architecture for the classification of metagenomics data based on the Convolutional Neural Networks, with the patristic distance defined on the phylogenetic tree being used as the proximity measure. The patristic distance between variables is used together with a sparsified version of MultiDimensional Scaling to embed the phylogenetic tree in a Euclidean space. Ph-CNN is tested with a domain adaptation approach on synthetic data and on a metagenomics collection of gut microbiota of 38 healthy subjects and 222 Inflammatory Bowel Disease patients, divided in 6 subclasses. Classification performance is promising when compared to classical algorithms like Support Vector Machines and Random Forest and a baseline fully connected neural network, e.g. the Multi-Layer Perceptron. Ph-CNN represents a novel deep learning approach for the classification of metagenomics data. Operatively, the algorithm has been implemented as a custom Keras layer taking care of passing to the following convolutional layer not only the data but also the ranked list of neighbourhood of each sample, thus mimicking the case of image data, transparently to the user.

Dynamic Construction Scheme for Virtualization Security Service in Software-Defined Networks

PubMed Central

Lin, Zhaowen; Tao, Dan; Wang, Zhenji

2017-01-01

For a Software Defined Network (SDN), security is an important factor affecting its large-scale deployment. The existing security solutions for SDN mainly focus on the controller itself, which has to handle all the security protection tasks by using the programmability of the network. This will undoubtedly involve a heavy burden for the controller. More devastatingly, once the controller itself is attacked, the entire network will be paralyzed. Motivated by this, this paper proposes a novel security protection architecture for SDN. We design a security service orchestration center in the control plane of SDN, and this center physically decouples from the SDN controller and constructs SDN security services. We adopt virtualization technology to construct a security meta-function library, and propose a dynamic security service composition construction algorithm based on web service composition technology. The rule-combining method is used to combine security meta-functions to construct security services which meet the requirements of users. Moreover, the RETE algorithm is introduced to improve the efficiency of the rule-combining method. We evaluate our solutions in a realistic scenario based on OpenStack. Substantial experimental results demonstrate the effectiveness of our solutions that contribute to achieve the effective security protection with a small burden of the SDN controller. PMID:28430155

Dynamic Construction Scheme for Virtualization Security Service in Software-Defined Networks.

PubMed

Lin, Zhaowen; Tao, Dan; Wang, Zhenji

2017-04-21

For a Software Defined Network (SDN), security is an important factor affecting its large-scale deployment. The existing security solutions for SDN mainly focus on the controller itself, which has to handle all the security protection tasks by using the programmability of the network. This will undoubtedly involve a heavy burden for the controller. More devastatingly, once the controller itself is attacked, the entire network will be paralyzed. Motivated by this, this paper proposes a novel security protection architecture for SDN. We design a security service orchestration center in the control plane of SDN, and this center physically decouples from the SDN controller and constructs SDN security services. We adopt virtualization technology to construct a security meta-function library, and propose a dynamic security service composition construction algorithm based on web service composition technology. The rule-combining method is used to combine security meta-functions to construct security services which meet the requirements of users. Moreover, the RETE algorithm is introduced to improve the efficiency of the rule-combining method. We evaluate our solutions in a realistic scenario based on OpenStack. Substantial experimental results demonstrate the effectiveness of our solutions that contribute to achieve the effective security protection with a small burden of the SDN controller.

Facial Emotions Recognition using Gabor Transform and Facial Animation Parameters with Neural Networks

NASA Astrophysics Data System (ADS)

Harit, Aditya; Joshi, J. C., Col; Gupta, K. K.

2018-03-01

The paper proposed an automatic facial emotion recognition algorithm which comprises of two main components: feature extraction and expression recognition. The algorithm uses a Gabor filter bank on fiducial points to find the facial expression features. The resulting magnitudes of Gabor transforms, along with 14 chosen FAPs (Facial Animation Parameters), compose the feature space. There are two stages: the training phase and the recognition phase. Firstly, for the present 6 different emotions, the system classifies all training expressions in 6 different classes (one for each emotion) in the training stage. In the recognition phase, it recognizes the emotion by applying the Gabor bank to a face image, then finds the fiducial points, and then feeds it to the trained neural architecture.

Optical linear algebra processors - Architectures and algorithms

NASA Technical Reports Server (NTRS)

Casasent, David

1986-01-01

Attention is given to the component design and optical configuration features of a generic optical linear algebra processor (OLAP) architecture, as well as the large number of OLAP architectures, number representations, algorithms and applications encountered in current literature. Number-representation issues associated with bipolar and complex-valued data representations, high-accuracy (including floating point) performance, and the base or radix to be employed, are discussed, together with case studies on a space-integrating frequency-multiplexed architecture and a hybrid space-integrating and time-integrating multichannel architecture.

Transmission over UWB channels with OFDM system using LDPC coding

NASA Astrophysics Data System (ADS)

Dziwoki, Grzegorz; Kucharczyk, Marcin; Sulek, Wojciech

2009-06-01

Hostile wireless environment requires use of sophisticated signal processing methods. The paper concerns on Ultra Wideband (UWB) transmission over Personal Area Networks (PAN) including MB-OFDM specification of physical layer. In presented work the transmission system with OFDM modulation was connected with LDPC encoder/decoder. Additionally the frame and bit error rate (FER and BER) of the system was decreased using results from the LDPC decoder in a kind of turbo equalization algorithm for better channel estimation. Computational block using evolutionary strategy, from genetic algorithms family, was also used in presented system. It was placed after SPA (Sum-Product Algorithm) decoder and is conditionally turned on in the decoding process. The result is increased effectiveness of the whole system, especially lower FER. The system was tested with two types of LDPC codes, depending on type of parity check matrices: randomly generated and constructed deterministically, optimized for practical decoder architecture implemented in the FPGA device.

Multivariate Spatial Condition Mapping Using Subtractive Fuzzy Cluster Means

PubMed Central

Sabit, Hakilo; Al-Anbuky, Adnan

2014-01-01

Wireless sensor networks are usually deployed for monitoring given physical phenomena taking place in a specific space and over a specific duration of time. The spatio-temporal distribution of these phenomena often correlates to certain physical events. To appropriately characterise these events-phenomena relationships over a given space for a given time frame, we require continuous monitoring of the conditions. WSNs are perfectly suited for these tasks, due to their inherent robustness. This paper presents a subtractive fuzzy cluster means algorithm and its application in data stream mining for wireless sensor systems over a cloud-computing-like architecture, which we call sensor cloud data stream mining. Benchmarking on standard mining algorithms, the k-means and the FCM algorithms, we have demonstrated that the subtractive fuzzy cluster means model can perform high quality distributed data stream mining tasks comparable to centralised data stream mining. PMID:25313495

Distributed Engine Control Empirical/Analytical Verification Tools

NASA Technical Reports Server (NTRS)

DeCastro, Jonathan; Hettler, Eric; Yedavalli, Rama; Mitra, Sayan

2013-01-01

NASA's vision for an intelligent engine will be realized with the development of a truly distributed control system featuring highly reliable, modular, and dependable components capable of both surviving the harsh engine operating environment and decentralized functionality. A set of control system verification tools was developed and applied to a C-MAPSS40K engine model, and metrics were established to assess the stability and performance of these control systems on the same platform. A software tool was developed that allows designers to assemble easily a distributed control system in software and immediately assess the overall impacts of the system on the target (simulated) platform, allowing control system designers to converge rapidly on acceptable architectures with consideration to all required hardware elements. The software developed in this program will be installed on a distributed hardware-in-the-loop (DHIL) simulation tool to assist NASA and the Distributed Engine Control Working Group (DECWG) in integrating DCS (distributed engine control systems) components onto existing and next-generation engines.The distributed engine control simulator blockset for MATLAB/Simulink and hardware simulator provides the capability to simulate virtual subcomponents, as well as swap actual subcomponents for hardware-in-the-loop (HIL) analysis. Subcomponents can be the communication network, smart sensor or actuator nodes, or a centralized control system. The distributed engine control blockset for MATLAB/Simulink is a software development tool. The software includes an engine simulation, a communication network simulation, control algorithms, and analysis algorithms set up in a modular environment for rapid simulation of different network architectures; the hardware consists of an embedded device running parts of the CMAPSS engine simulator and controlled through Simulink. The distributed engine control simulation, evaluation, and analysis technology provides unique capabilities to study the effects of a given change to the control system in the context of the distributed paradigm. The simulation tool can support treatment of all components within the control system, both virtual and real; these include communication data network, smart sensor and actuator nodes, centralized control system (FADEC full authority digital engine control), and the aircraft engine itself. The DECsim tool can allow simulation-based prototyping of control laws, control architectures, and decentralization strategies before hardware is integrated into the system. With the configuration specified, the simulator allows a variety of key factors to be systematically assessed. Such factors include control system performance, reliability, weight, and bandwidth utilization.

Solving the Cauchy-Riemann equations on parallel computers

NASA Technical Reports Server (NTRS)

Fatoohi, Raad A.; Grosch, Chester E.

1987-01-01

Discussed is the implementation of a single algorithm on three parallel-vector computers. The algorithm is a relaxation scheme for the solution of the Cauchy-Riemann equations; a set of coupled first order partial differential equations. The computers were chosen so as to encompass a variety of architectures. They are: the MPP, and SIMD machine with 16K bit serial processors; FLEX/32, an MIMD machine with 20 processors; and CRAY/2, an MIMD machine with four vector processors. The machine architectures are briefly described. The implementation of the algorithm is discussed in relation to these architectures and measures of the performance on each machine are given. Simple performance models are used to describe the performance. These models highlight the bottlenecks and limiting factors for this algorithm on these architectures. Conclusions are presented.

18F-FDG PET brain images as features for Alzheimer classification

NASA Astrophysics Data System (ADS)

Azmi, M. H.; Saripan, M. I.; Nordin, A. J.; Ahmad Saad, F. F.; Abdul Aziz, S. A.; Wan Adnan, W. A.

2017-08-01

2-Deoxy-2-[fluorine-18] fluoro-D-glucose (18F-FDG) Positron Emission Tomography (PET) imaging offers meaningful information for various types of diseases diagnosis. In Alzheimer's disease (AD), the hypometabolism of glucose which observed on the low intensity voxel in PET image may relate to the onset of the disease. The importance of early detection of AD is inevitable because the resultant brain damage is irreversible. Several statistical analysis and machine learning algorithm have been proposed to investigate the rate and the pattern of the hypometabolism. This study focus on the same aim with further investigation was performed on several hypometabolism pattern. Some pre-processing steps were implemented to standardize the data in order to minimize the effect of resolution and anatomical differences. The features used are the mean voxel intensity within the AD pattern mask, which derived from several z-score and FDR threshold values. The global mean voxel (GMV) and slice-based mean voxel (SbMV) intensity were observed and used as input to the neural network. Several neural network architectures were tested and compared to the nearest neighbour method. The highest accuracy equals to 0.9 and recorded at z-score ≤-1.3 with 1 node neural network architecture (sensitivity=0.81 and specificity=0.95) and at z-score ≤-0.7 with 10 nodes neural network (sensitivity=0.83 and specificity=0.94).

The probabilistic neural network architecture for high speed classification of remotely sensed imagery

NASA Technical Reports Server (NTRS)

Chettri, Samir R.; Cromp, Robert F.

1993-01-01

In this paper we discuss a neural network architecture (the Probabilistic Neural Net or the PNN) that, to the best of our knowledge, has not previously been applied to remotely sensed data. The PNN is a supervised non-parametric classification algorithm as opposed to the Gaussian maximum likelihood classifier (GMLC). The PNN works by fitting a Gaussian kernel to each training point. The width of the Gaussian is controlled by a tuning parameter called the window width. If very small widths are used, the method is equivalent to the nearest neighbor method. For large windows, the PNN behaves like the GMLC. The basic implementation of the PNN requires no training time at all. In this respect it is far better than the commonly used backpropagation neural network which can be shown to take O(N6) time for training where N is the dimensionality of the input vector. In addition the PNN can be implemented in a feed forward mode in hardware. The disadvantage of the PNN is that it requires all the training data to be stored. Some solutions to this problem are discussed in the paper. Finally, we discuss the accuracy of the PNN with respect to the GMLC and the backpropagation neural network (BPNN). The PNN is shown to be better than GMLC and not as good as the BPNN with regards to classification accuracy.

Evolution of a designless nanoparticle network into reconfigurable Boolean logic

NASA Astrophysics Data System (ADS)

Bose, S. K.; Lawrence, C. P.; Liu, Z.; Makarenko, K. S.; van Damme, R. M. J.; Broersma, H. J.; van der Wiel, W. G.

2015-12-01

Natural computers exploit the emergent properties and massive parallelism of interconnected networks of locally active components. Evolution has resulted in systems that compute quickly and that use energy efficiently, utilizing whatever physical properties are exploitable. Man-made computers, on the other hand, are based on circuits of functional units that follow given design rules. Hence, potentially exploitable physical processes, such as capacitive crosstalk, to solve a problem are left out. Until now, designless nanoscale networks of inanimate matter that exhibit robust computational functionality had not been realized. Here we artificially evolve the electrical properties of a disordered nanomaterials system (by optimizing the values of control voltages using a genetic algorithm) to perform computational tasks reconfigurably. We exploit the rich behaviour that emerges from interconnected metal nanoparticles, which act as strongly nonlinear single-electron transistors, and find that this nanoscale architecture can be configured in situ into any Boolean logic gate. This universal, reconfigurable gate would require about ten transistors in a conventional circuit. Our system meets the criteria for the physical realization of (cellular) neural networks: universality (arbitrary Boolean functions), compactness, robustness and evolvability, which implies scalability to perform more advanced tasks. Our evolutionary approach works around device-to-device variations and the accompanying uncertainties in performance. Moreover, it bears a great potential for more energy-efficient computation, and for solving problems that are very hard to tackle in conventional architectures.

Optical neural network system for pose determination of spinning satellites

NASA Technical Reports Server (NTRS)

Lee, Andrew; Casasent, David

1990-01-01

An optical neural network architecture and algorithm based on a Hopfield optimization network are presented for multitarget tracking. This tracker utilizes a neuron for every possible target track, and a quadratic energy function of neural activities which is minimized using gradient descent neural evolution. The neural net tracker is demonstrated as part of a system for determining position and orientation (pose) of spinning satellites with respect to a robotic spacecraft. The input to the system is time sequence video from a single camera. Novelty detection and filtering are utilized to locate and segment novel regions from the input images. The neural net multitarget tracker determines the correspondences (or tracks) of the novel regions as a function of time, and hence the paths of object (satellite) parts. The path traced out by a given part or region is approximately elliptical in image space, and the position, shape and orientation of the ellipse are functions of the satellite geometry and its pose. Having a geometric model of the satellite, and the elliptical path of a part in image space, the three-dimensional pose of the satellite is determined. Digital simulation results using this algorithm are presented for various satellite poses and lighting conditions.

Implementation study of an analog spiking neural network for assisting cardiac delay prediction in a cardiac resynchronization therapy device.

PubMed

Sun, Qing; Schwartz, François; Michel, Jacques; Herve, Yannick; Dalmolin, Renzo

2011-06-01

In this paper, we aim at developing an analog spiking neural network (SNN) for reinforcing the performance of conventional cardiac resynchronization therapy (CRT) devices (also called biventricular pacemakers). Targeting an alternative analog solution in 0.13- μm CMOS technology, this paper proposes an approach to improve cardiac delay predictions in every cardiac period in order to assist the CRT device to provide real-time optimal heartbeats. The primary analog SNN architecture is proposed and its implementation is studied to fulfill the requirement of very low energy consumption. By using the Hebbian learning and reinforcement learning algorithms, the intended adaptive CRT device works with different functional modes. The simulations of both learning algorithms have been carried out, and they were shown to demonstrate the global functionalities. To improve the realism of the system, we introduce various heart behavior models (with constant/variable heart rates) that allow pathologic simulations with/without noise on the signals of the input sensors. The simulations of the global system (pacemaker models coupled with heart models) have been investigated and used to validate the analog spiking neural network implementation.

Parallel mutual information estimation for inferring gene regulatory networks on GPUs

PubMed Central

2011-01-01

Background Mutual information is a measure of similarity between two variables. It has been widely used in various application domains including computational biology, machine learning, statistics, image processing, and financial computing. Previously used simple histogram based mutual information estimators lack the precision in quality compared to kernel based methods. The recently introduced B-spline function based mutual information estimation method is competitive to the kernel based methods in terms of quality but at a lower computational complexity. Results We present a new approach to accelerate the B-spline function based mutual information estimation algorithm with commodity graphics hardware. To derive an efficient mapping onto this type of architecture, we have used the Compute Unified Device Architecture (CUDA) programming model to design and implement a new parallel algorithm. Our implementation, called CUDA-MI, can achieve speedups of up to 82 using double precision on a single GPU compared to a multi-threaded implementation on a quad-core CPU for large microarray datasets. We have used the results obtained by CUDA-MI to infer gene regulatory networks (GRNs) from microarray data. The comparisons to existing methods including ARACNE and TINGe show that CUDA-MI produces GRNs of higher quality in less time. Conclusions CUDA-MI is publicly available open-source software, written in CUDA and C++ programming languages. It obtains significant speedup over sequential multi-threaded implementation by fully exploiting the compute capability of commonly used CUDA-enabled low-cost GPUs. PMID:21672264

An Adaptive Flow Solver for Air-Borne Vehicles Undergoing Time-Dependent Motions/Deformations

NASA Technical Reports Server (NTRS)

Singh, Jatinder; Taylor, Stephen

1997-01-01

This report describes a concurrent Euler flow solver for flows around complex 3-D bodies. The solver is based on a cell-centered finite volume methodology on 3-D unstructured tetrahedral grids. In this algorithm, spatial discretization for the inviscid convective term is accomplished using an upwind scheme. A localized reconstruction is done for flow variables which is second order accurate. Evolution in time is accomplished using an explicit three-stage Runge-Kutta method which has second order temporal accuracy. This is adapted for concurrent execution using another proven methodology based on concurrent graph abstraction. This solver operates on heterogeneous network architectures. These architectures may include a broad variety of UNIX workstations and PCs running Windows NT, symmetric multiprocessors and distributed-memory multi-computers. The unstructured grid is generated using commercial grid generation tools. The grid is automatically partitioned using a concurrent algorithm based on heat diffusion. This results in memory requirements that are inversely proportional to the number of processors. The solver uses automatic granularity control and resource management techniques both to balance load and communication requirements, and deal with differing memory constraints. These ideas are again based on heat diffusion. Results are subsequently combined for visualization and analysis using commercial CFD tools. Flow simulation results are demonstrated for a constant section wing at subsonic, transonic, and a supersonic case. These results are compared with experimental data and numerical results of other researchers. Performance results are under way for a variety of network topologies.

A Multiobjective Sparse Feature Learning Model for Deep Neural Networks.

PubMed

Gong, Maoguo; Liu, Jia; Li, Hao; Cai, Qing; Su, Linzhi

2015-12-01

Hierarchical deep neural networks are currently popular learning models for imitating the hierarchical architecture of human brain. Single-layer feature extractors are the bricks to build deep networks. Sparse feature learning models are popular models that can learn useful representations. But most of those models need a user-defined constant to control the sparsity of representations. In this paper, we propose a multiobjective sparse feature learning model based on the autoencoder. The parameters of the model are learnt by optimizing two objectives, reconstruction error and the sparsity of hidden units simultaneously to find a reasonable compromise between them automatically. We design a multiobjective induced learning procedure for this model based on a multiobjective evolutionary algorithm. In the experiments, we demonstrate that the learning procedure is effective, and the proposed multiobjective model can learn useful sparse features.

Traffic shaping and scheduling for OBS-based IP/WDM backbones

NASA Astrophysics Data System (ADS)

Elhaddad, Mahmoud S.; Melhem, Rami G.; Znati, Taieb; Basak, Debashis

2003-10-01

We introduce Proactive Reservation-based Switching (PRS) -- a switching architecture for IP/WDM networks based on Labeled Optical Burst Switching. PRS achieves packet delay and loss performance comparable to that of packet-switched networks, without requiring large buffering capacity, or burst scheduling across a large number of wavelengths at the core routers. PRS combines proactive channel reservation with periodic shaping of ingress-egress traffic aggregates to hide the offset latency and approximate the utilization/buffering characteristics of discrete-time queues with periodic arrival streams. A channel scheduling algorithm imposes constraints on burst departure times to ensure efficient utilization of wavelength channels and to maintain the distance between consecutive bursts through the network. Results obtained from simulation using TCP traffic over carefully designed topologies indicate that PRS consistently achieves channel utilization above 90% with modest buffering requirements.

The GOES-R Product Generation Architecture - Post CDR Update

NASA Astrophysics Data System (ADS)

Dittberner, G.; Kalluri, S.; Weiner, A.

2012-12-01

The GOES-R system will substantially improve the accuracy of information available to users by providing data from significantly enhanced instruments, which will generate an increased number and diversity of products with higher resolution, and much shorter relook times. Considerably greater compute and memory resources are necessary to achieve the necessary latency and availability for these products. Over time, new and updated algorithms are expected to be added and old ones removed as science advances and new products are developed. The GOES-R GS architecture is being planned to maintain functionality so that when such changes are implemented, operational product generation will continue without interruption. The primary parts of the PG infrastructure are the Service Based Architecture (SBA) and the Data Fabric (DF). SBA is the middleware that encapsulates and manages science algorithms that generate products. It is divided into three parts, the Executive, which manages and configures the algorithm as a service, the Dispatcher, which provides data to the algorithm, and the Strategy, which determines when the algorithm can execute with the available data. SBA is a distributed architecture, with services connected to each other over a compute grid and is highly scalable. This plug-and-play architecture allows algorithms to be added, removed, or updated without affecting any other services or software currently running and producing data. Algorithms require product data from other algorithms, so a scalable and reliable messaging is necessary. The SBA uses the DF to provide this data communication layer between algorithms. The DF provides an abstract interface over a distributed and persistent multi-layered storage system (e.g., memory based caching above disk-based storage) and an event management system that allows event-driven algorithm services to know when instrument data are available and where they reside. Together, the SBA and the DF provide a flexible, high performance architecture that can meet the needs of product processing now and as they grow in the future.

A regularization approach to continuous learning with an application to financial derivatives pricing.

PubMed

Ormoneit, D

1999-12-01

We consider the training of neural networks in cases where the nonlinear relationship of interest gradually changes over time. One possibility to deal with this problem is by regularization where a variation penalty is added to the usual mean squared error criterion. To learn the regularized network weights we suggest the Iterative Extended Kalman Filter (IEKF) as a learning rule, which may be derived from a Bayesian perspective on the regularization problem. A primary application of our algorithm is in financial derivatives pricing, where neural networks may be used to model the dependency of the derivatives' price on one or several underlying assets. After giving a brief introduction to the problem of derivatives pricing we present experiments with German stock index options data showing that a regularized neural network trained with the IEKF outperforms several benchmark models and alternative learning procedures. In particular, the performance may be greatly improved using a newly designed neural network architecture that accounts for no-arbitrage pricing restrictions.

Prioritized retransmission in slotted all-optical packet-switched networks

NASA Astrophysics Data System (ADS)

Ghaffar Pour Rahbar, Akbar; Yang, Oliver

2006-12-01

We consider an all-optical slotted packet-switched network interconnected by a number of bufferless all-optical switches with contention-based operation. One approach to reduce the cost of the expensive contention resolution hardware could be retransmission in which each ingress switch keeps a copy of the transmitted traffic in the electronic buffer and retransmits whenever required. The conventional retransmission technique may need a higher number of retransmissions until traffic passes through the network. This in turn may lead to a retransmission at a higher layer and reduce the network throughput. In this paper, we propose and analyze a simple but effective prioritized retransmission technique in which dropped traffic is prioritized when retransmitted from ingress switches so that the core switch can process them with a higher priority. We present the analysis of both techniques in multifiber network architecture and verify it via simulation to demonstrate that our proposed algorithm can limit the number of retransmissions significantly and can improve TCP throughput better than the conventional retransmission technique.

Intelligent Elements for ISHM

NASA Technical Reports Server (NTRS)

Schmalzel, John L.; Morris, Jon; Turowski, Mark; Figueroa, Fernando; Oostdyk, Rebecca

2008-01-01

There are a number of architecture models for implementing Integrated Systems Health Management (ISHM) capabilities. For example, approaches based on the OSA-CBM and OSA-EAI models, or specific architectures developed in response to local needs. NASA s John C. Stennis Space Center (SSC) has developed one such version of an extensible architecture in support of rocket engine testing that integrates a palette of functions in order to achieve an ISHM capability. Among the functional capabilities that are supported by the framework are: prognostic models, anomaly detection, a data base of supporting health information, root cause analysis, intelligent elements, and integrated awareness. This paper focuses on the role that intelligent elements can play in ISHM architectures. We define an intelligent element as a smart element with sufficient computing capacity to support anomaly detection or other algorithms in support of ISHM functions. A smart element has the capabilities of supporting networked implementations of IEEE 1451.x smart sensor and actuator protocols. The ISHM group at SSC has been actively developing intelligent elements in conjunction with several partners at other Centers, universities, and companies as part of our ISHM approach for better supporting rocket engine testing. We have developed several implementations. Among the key features for these intelligent sensors is support for IEEE 1451.1 and incorporation of a suite of algorithms for determination of sensor health. Regardless of the potential advantages that can be achieved using intelligent sensors, existing large-scale systems are still based on conventional sensors and data acquisition systems. In order to bring the benefits of intelligent sensors to these environments, we have also developed virtual implementations of intelligent sensors.

Classification of amyotrophic lateral sclerosis disease based on convolutional neural network and reinforcement sample learning algorithm.

PubMed

Sengur, Abdulkadir; Akbulut, Yaman; Guo, Yanhui; Bajaj, Varun

2017-12-01

Electromyogram (EMG) signals contain useful information of the neuromuscular diseases like amyotrophic lateral sclerosis (ALS). ALS is a well-known brain disease, which can progressively degenerate the motor neurons. In this paper, we propose a deep learning based method for efficient classification of ALS and normal EMG signals. Spectrogram, continuous wavelet transform (CWT), and smoothed pseudo Wigner-Ville distribution (SPWVD) have been employed for time-frequency (T-F) representation of EMG signals. A convolutional neural network is employed to classify these features. In it, Two convolution layers, two pooling layer, a fully connected layer and a lost function layer is considered in CNN architecture. The CNN architecture is trained with the reinforcement sample learning strategy. The efficiency of the proposed implementation is tested on publicly available EMG dataset. The dataset contains 89 ALS and 133 normal EMG signals with 24 kHz sampling frequency. Experimental results show 96.80% accuracy. The obtained results are also compared with other methods, which show the superiority of the proposed method.

Equivalence of restricted Boltzmann machines and tensor network states

NASA Astrophysics Data System (ADS)

Chen, Jing; Cheng, Song; Xie, Haidong; Wang, Lei; Xiang, Tao

2018-02-01

The restricted Boltzmann machine (RBM) is one of the fundamental building blocks of deep learning. RBM finds wide applications in dimensional reduction, feature extraction, and recommender systems via modeling the probability distributions of a variety of input data including natural images, speech signals, and customer ratings, etc. We build a bridge between RBM and tensor network states (TNS) widely used in quantum many-body physics research. We devise efficient algorithms to translate an RBM into the commonly used TNS. Conversely, we give sufficient and necessary conditions to determine whether a TNS can be transformed into an RBM of given architectures. Revealing these general and constructive connections can cross fertilize both deep learning and quantum many-body physics. Notably, by exploiting the entanglement entropy bound of TNS, we can rigorously quantify the expressive power of RBM on complex data sets. Insights into TNS and its entanglement capacity can guide the design of more powerful deep learning architectures. On the other hand, RBM can represent quantum many-body states with fewer parameters compared to TNS, which may allow more efficient classical simulations.

Efficient SCT Protocol for Post Disaster Communication

NASA Astrophysics Data System (ADS)

Ramesh, T. K.; Giriraja, C. V.

2017-08-01

Natural and catastrophic disasters can cause damage to the communication system, the damage may be complete or it may be partial. In such areas communication and exchange of information plays a very important role and become difficult to happen in such situations. So, the rescue systems should be installed in those areas for the rescue operations and to take important decisions about how to make a connection from there to the outside world. Wireless communication network architecture should be setup in disaster areas for the communication to happen and to gather information. Wireless ad-hoc network architecture is proposed in this paper with access nodes. These access nodes acts as hotspot for certain area in which they are set up such that the Wi-Fi capable devices get connected to them for communication to happen. If the mobile battery is drained in such situations wireless charging using microwave is shown in this paper. Performance analysis of the communication transport layer protocols is shown and Efficient SCTP (ESTP) algorithm is developed which shows better results in terms of cumulative packet loss.

A Novel Optical/digital Processing System for Pattern Recognition

NASA Technical Reports Server (NTRS)

Boone, Bradley G.; Shukla, Oodaye B.

1993-01-01

This paper describes two processing algorithms that can be implemented optically: the Radon transform and angular correlation. These two algorithms can be combined in one optical processor to extract all the basic geometric and amplitude features from objects embedded in video imagery. We show that the internal amplitude structure of objects is recovered by the Radon transform, which is a well-known result, but, in addition, we show simulation results that calculate angular correlation, a simple but unique algorithm that extracts object boundaries from suitably threshold images from which length, width, area, aspect ratio, and orientation can be derived. In addition to circumventing scale and rotation distortions, these simulations indicate that the features derived from the angular correlation algorithm are relatively insensitive to tracking shifts and image noise. Some optical architecture concepts, including one based on micro-optical lenslet arrays, have been developed to implement these algorithms. Simulation test and evaluation using simple synthetic object data will be described, including results of a study that uses object boundaries (derivable from angular correlation) to classify simple objects using a neural network.

The composition of engineered cartilage at the time of implantation determines the likelihood of regenerating tissue with a normal collagen architecture.

PubMed

Nagel, Thomas; Kelly, Daniel J

2013-04-01

The biomechanical functionality of articular cartilage is derived from both its biochemical composition and the architecture of the collagen network. Failure to replicate this normal Benninghoff architecture in regenerating articular cartilage may in turn predispose the tissue to failure. In this article, the influence of the maturity (or functionality) of a tissue-engineered construct at the time of implantation into a tibial chondral defect on the likelihood of recapitulating a normal Benninghoff architecture was investigated using a computational model featuring a collagen remodeling algorithm. Such a normal tissue architecture was predicted to form in the intact tibial plateau due to the interplay between the depth-dependent extracellular matrix properties, foremost swelling pressures, and external mechanical loading. In the presence of even small empty defects in the articular surface, the collagen architecture in the surrounding cartilage was predicted to deviate significantly from the native state, indicating a possible predisposition for osteoarthritic changes. These negative alterations were alleviated by the implantation of tissue-engineered cartilage, where a mature implant was predicted to result in the formation of a more native-like collagen architecture than immature implants. The results of this study highlight the importance of cartilage graft functionality to maintain and/or re-establish joint function and suggest that engineering a tissue with a native depth-dependent composition may facilitate the establishment of a normal Benninghoff collagen architecture after implantation into load-bearing defects.

Massively parallel algorithms for real-time wavefront control of a dense adaptive optics system

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

Fijany, A.; Milman, M.; Redding, D.

1994-12-31

In this paper massively parallel algorithms and architectures for real-time wavefront control of a dense adaptive optic system (SELENE) are presented. The authors have already shown that the computation of a near optimal control algorithm for SELENE can be reduced to the solution of a discrete Poisson equation on a regular domain. Although, this represents an optimal computation, due the large size of the system and the high sampling rate requirement, the implementation of this control algorithm poses a computationally challenging problem since it demands a sustained computational throughput of the order of 10 GFlops. They develop a novel algorithm,more » designated as Fast Invariant Imbedding algorithm, which offers a massive degree of parallelism with simple communication and synchronization requirements. Due to these features, this algorithm is significantly more efficient than other Fast Poisson Solvers for implementation on massively parallel architectures. The authors also discuss two massively parallel, algorithmically specialized, architectures for low-cost and optimal implementation of the Fast Invariant Imbedding algorithm.« less