Fernandez, Michael; Caballero, Julio; Fernandez, Leyden; Sarai, Akinori
2011-02-01
Many articles in "in silico" drug design implemented genetic algorithm (GA) for feature selection, model optimization, conformational search, or docking studies. Some of these articles described GA applications to quantitative structure-activity relationships (QSAR) modeling in combination with regression and/or classification techniques. We reviewed the implementation of GA in drug design QSAR and specifically its performance in the optimization of robust mathematical models such as Bayesian-regularized artificial neural networks (BRANNs) and support vector machines (SVMs) on different drug design problems. Modeled data sets encompassed ADMET and solubility properties, cancer target inhibitors, acetylcholinesterase inhibitors, HIV-1 protease inhibitors, ion-channel and calcium entry blockers, and antiprotozoan compounds as well as protein classes, functional, and conformational stability data. The GA-optimized predictors were often more accurate and robust than previous published models on the same data sets and explained more than 65% of data variances in validation experiments. In addition, feature selection over large pools of molecular descriptors provided insights into the structural and atomic properties ruling ligand-target interactions.
Zhang, Ridong; Tao, Jili; Lu, Renquan; Jin, Qibing
2016-12-08
Modeling of distributed parameter systems is difficult because of their nonlinearity and infinite-dimensional characteristics. Based on principal component analysis (PCA), a hybrid modeling strategy that consists of a decoupled linear autoregressive exogenous (ARX) model and a nonlinear radial basis function (RBF) neural network model are proposed. The spatial-temporal output is first divided into a few dominant spatial basis functions and finite-dimensional temporal series by PCA. Then, a decoupled ARX model is designed to model the linear dynamics of the dominant modes of the time series. The nonlinear residual part is subsequently parameterized by RBFs, where genetic algorithm is utilized to optimize their hidden layer structure and the parameters. Finally, the nonlinear spatial-temporal dynamic system is obtained after the time/space reconstruction. Simulation results of a catalytic rod and a heat conduction equation demonstrate the effectiveness of the proposed strategy compared to several other methods.
Cherniak, Christopher
2012-01-01
Combinatorial network optimization theory concerns minimization of connection costs among interconnected components in systems such as electronic circuits. As an organization principle, similar wiring minimization can be observed at various levels of nervous systems, invertebrate and vertebrate, including primate, from placement of the entire brain in the body down to the subcellular level of neuron arbor geometry. In some cases, the minimization appears either perfect, or as good as can be detected with current methods. One question such best-of-all-possible-brains results raise is, what is the map of such optimization, does it have a distinct neural domain?
Forecasting of Market Clearing Price by Using GA Based Neural Network
NASA Astrophysics Data System (ADS)
Yang, Bo; Chen, Yun-Ping; Zhao, Zun-Lian; Han, Qi-Ye
Forecasting of Market Clearing Price (MCP) is important to economic benefits of electricity market participants. To accurately forecast MCP, a novel two-stage GA-based neural network model (GA-NN) is proposed. In the first stage, GA chromosome is designed into two parts: boolean coding part for neural network topology and real coding part for connection weights. By hybrid genetic operation of selection, crossover and mutation under the criterion of error minimization between the actual output and the desired output, optimal architecture of neural network is obtained. In the second stage, gradient learning algorithm with momentum rate is imposed on neural network with optimal architecture. After learning process, optimal connection weights are obtained. The proposed model is tested on MCP forecasting in California electricity market. The test results show that GA-NN has self-adaptive ability in its topology and connection weights and can obtain more accurate MCP forecasting values than BP neural network.
Novel model of a AlGaN/GaN high electron mobility transistor based on an artificial neural network
NASA Astrophysics Data System (ADS)
Cheng, Zhi-Qun; Hu, Sha; Liu, Jun; Zhang, Qi-Jun
2011-03-01
In this paper we present a novel approach to modeling AlGaN/GaN high electron mobility transistor (HEMT) with an artificial neural network (ANN). The AlGaN/GaN HEMT device structure and its fabrication process are described. The circuit-based Neuro-space mapping (neuro-SM) technique is studied in detail. The EEHEMT model is implemented according to the measurement results of the designed device, which serves as a coarse model. An ANN is proposed to model AlGaN/GaN HEMT based on the coarse model. Its optimization is performed. The simulation results from the model are compared with the measurement results. It is shown that the simulation results obtained from the ANN model of AlGaN/GaN HEMT are more accurate than those obtained from the EEHEMT model. Project supported by the National Natural Science Foundation of China (Grant No. 60776052).
Electronic neural networks for global optimization
NASA Technical Reports Server (NTRS)
Thakoor, A. P.; Moopenn, A. W.; Eberhardt, S.
1990-01-01
An electronic neural network with feedback architecture, implemented in analog custom VLSI is described. Its application to problems of global optimization for dynamic assignment is discussed. The convergence properties of the neural network hardware are compared with computer simulation results. The neural network's ability to provide optimal or near optimal solutions within only a few neuron time constants, a speed enhancement of several orders of magnitude over conventional search methods, is demonstrated. The effect of noise on the circuit dynamics and the convergence behavior of the neural network hardware is also examined.
Groundwater remediation optimization using artificial neural networks
Rogers, L. L., LLNL
1998-05-01
One continuing point of research in optimizing groundwater quality management is reduction of computational burden which is particularly limiting in field-scale applications. Often evaluation of a single pumping strategy, i.e. one call to the groundwater flow and transport model (GFTM) may take several hours on a reasonably fast workstation. For computational flexibility and efficiency, optimal groundwater remediation design at Lawrence Livermore National Laboratory (LLNL) has relied on artificial neural networks (ANNS) trained to approximate the outcome of 2-D field-scale, finite difference/finite element GFTMs. The search itself has been directed primarily by the genetic algorithm (GA) or the simulated annealing (SA) algorithm. This approach has advantages of (1) up to a million fold increase in speed of remediation pattern assessment during the searches and sensitivity analyses for the 2-D LLNL work, (2) freedom from sequential runs of the GFTM (enables workstation farming), and (3) recycling of the knowledge base (i.e. runs of the GFTM necessary to train the ANNS). Reviewed here are the background and motivation for such work, recent applications, and continuing issues of research.
Adaptive optimization and control using neural networks
Mead, W.C.; Brown, S.K.; Jones, R.D.; Bowling, P.S.; Barnes, C.W.
1993-10-22
Recent work has demonstrated the ability of neural-network-based controllers to optimize and control machines with complex, non-linear, relatively unknown control spaces. We present a brief overview of neural networks via a taxonomy illustrating some capabilities of different kinds of neural networks. We present some successful control examples, particularly the optimization and control of a small-angle negative ion source.
High-Gain AlxGa1-xAs/GaAs Transistors For Neural Networks
NASA Technical Reports Server (NTRS)
Kim, Jae-Hoon; Lin, Steven H.
1991-01-01
High-gain AlxGa1-xAs/GaAs npn double heterojunction bipolar transistors developed for use as phototransistors in optoelectronic integrated circuits, especially in artificial neural networks. Transistors perform both photodetection and saturating-amplification functions of neurons. Good candidates for such application because structurally compatible with laser diodes and light-emitting diodes, detect light, and provide high current gain needed to compensate for losses in holographic optical elements.
2013-08-01
Growth and Optimization of 2-μm InGaSb/AlGaSb Quantum-Well-Based VECSELs on GaAs/AlGaAs DBRs Report Title ABSTRACT We report the growth of...optically pumped vertical-external-cavity surface-emitting lasers ( VECSELs ) based on InGaSb/AlGaSb quantum wells grown on GaAs/AlGaAs distributed Bragg...results in spontaneous relaxation of the GaSb epilayer and also significantly reduces the threading dislocation density. The VECSELs are operated in both
Predictive control of SOFC based on a GA-RBF neural network model
NASA Astrophysics Data System (ADS)
Wu, Xiao-Juan; Zhu, Xin-Jian; Cao, Guang-Yi; Tu, Heng-Yong
Transients in a load have a significant impact on the performance and durability of a solid oxide fuel cell (SOFC) system. One of the main reasons is that the fuel utilization changes drastically due to the load change. Therefore, in order to guarantee the fuel utilization to operate within a safe range, a nonlinear model predictive control (MPC) method is proposed to control the stack terminal voltage as a proper constant in this paper. The nonlinear predictive controller is based on an improved radial basis function (RBF) neural network identification model. During the process of modeling, the genetic algorithm (GA) is used to optimize the parameters of RBF neural networks. And then a nonlinear predictive control algorithm is applied to track the voltage of the SOFC. Compared with the constant fuel utilization control method, the simulation results show that the nonlinear predictive control algorithm based on the GA-RBF model performs much better.
Optimized structure of AlGaAs/GaAs double junction solar cells
NASA Astrophysics Data System (ADS)
Bahrami, Ali; Mohammadnejad, Shahram; Jouyandeh Abkenar, Nima
2014-04-01
In this paper, the sub-layers of AlGaAs/GaAs double junction (DJ) solar cell have been redesigned in order to achieve an optimum cell structure. It has been deduced with cooperation of detailed balance limit theory and structural behaviour of AlGaAs, that the Al0.45Ga0.55As is the best choice for top cell's material in AlGaAs/GaAs DJ solar cell. Also, there is a trade-off between peak tunnelling current and transparency in tunnel junction which makes Al0.07Ga0.93As as the optimum tunnel junction of AlGaAs/GaAs cell. Finally, a smoothed reflectance senary-layer structure based on modified-DBR has been proposed to be used as anti-reflection coating of proposed structure. Also, the thickness and doping concentration level of different layers have been optimized.
Manipulator inverse kinematics control based on particle swarm optimization neural network
NASA Astrophysics Data System (ADS)
Wen, Xiulan; Sheng, Danghong; Guo, Jing
2008-10-01
The inverse kinematics control of a robotic manipulator requires solving non-linear equations having transcendental functions and involving time-consuming calculations. Particle Swarm Optimization (PSO), which is based on the behaviour of insect swarms and exploits the solution space by taking into account the experience of the single particle as well as that of the entire swarm, is similar to the genetic algorithm (GA) in that it performs a structured randomized search of an unknown parameter space by manipulating a population of parameter estimates to converge on a suitable solution. In this paper, PSO is firstly proposed to optimize feed-forward neural network for manipulator inverse kinematics. Compared with the results of the fast back propagation learning algorithm (FBP), conventional GA genetic algorithm based elitist reservation (EGA), improved GA (IGA) and immune evolutionary computation (IEC), the simulation results verify the particle swarm optimization neural network (PSONN) is effective for manipulator inverse kinematics control.
On sparsely connected optimal neural networks
Beiu, V.; Draghici, S.
1997-10-01
This paper uses two different approaches to show that VLSI- and size-optimal discrete neural networks are obtained for small fan-in values. These have applications to hardware implementations of neural networks, but also reveal an intrinsic limitation of digital VLSI technology: its inability to cope with highly connected structures. The first approach is based on implementing F{sub n,m} functions. The authors show that this class of functions can be implemented in VLSI-optimal (i.e., minimizing AT{sup 2}) neural networks of small constant fan-ins. In order to estimate the area (A) and the delay (T) of such networks, the following cost functions will be used: (i) the connectivity and the number-of-bits for representing the weights and thresholds--for good estimates of the area; and (ii) the fan-ins and the length of the wires--for good approximates of the delay. The second approach is based on implementing Boolean functions for which the classical Shannon`s decomposition can be used. Such a solution has already been used to prove bounds on the size of fan-in 2 neural networks. They will generalize the result presented there to arbitrary fan-in, and prove that the size is minimized by small fan-in values. Finally, a size-optimal neural network of small constant fan-ins will be suggested for F{sub n,m} functions.
Optimal Decision Making in Neural Inhibition Models
ERIC Educational Resources Information Center
van Ravenzwaaij, Don; van der Maas, Han L. J.; Wagenmakers, Eric-Jan
2012-01-01
In their influential "Psychological Review" article, Bogacz, Brown, Moehlis, Holmes, and Cohen (2006) discussed optimal decision making as accomplished by the drift diffusion model (DDM). The authors showed that neural inhibition models, such as the leaky competing accumulator model (LCA) and the feedforward inhibition model (FFI), can mimic the…
Optimal Decision Making in Neural Inhibition Models
ERIC Educational Resources Information Center
van Ravenzwaaij, Don; van der Maas, Han L. J.; Wagenmakers, Eric-Jan
2012-01-01
In their influential "Psychological Review" article, Bogacz, Brown, Moehlis, Holmes, and Cohen (2006) discussed optimal decision making as accomplished by the drift diffusion model (DDM). The authors showed that neural inhibition models, such as the leaky competing accumulator model (LCA) and the feedforward inhibition model (FFI), can mimic the…
The prediction in computer color matching of dentistry based on GA+BP neural network.
Li, Haisheng; Lai, Long; Chen, Li; Lu, Cheng; Cai, Qiang
2015-01-01
Although the use of computer color matching can reduce the influence of subjective factors by technicians, matching the color of a natural tooth with a ceramic restoration is still one of the most challenging topics in esthetic prosthodontics. Back propagation neural network (BPNN) has already been introduced into the computer color matching in dentistry, but it has disadvantages such as unstable and low accuracy. In our study, we adopt genetic algorithm (GA) to optimize the initial weights and threshold values in BPNN for improving the matching precision. To our knowledge, we firstly combine the BPNN with GA in computer color matching in dentistry. Extensive experiments demonstrate that the proposed method improves the precision and prediction robustness of the color matching in restorative dentistry.
Optimal attentional modulation of a neural population
Borji, Ali; Itti, Laurent
2014-01-01
Top-down attention has often been separately studied in the contexts of either optimal population coding or biasing of visual search. Yet, both are intimately linked, as they entail optimally modulating sensory variables in neural populations according to top-down goals. Designing experiments to probe top-down attentional modulation is difficult because non-linear population dynamics are hard to predict in the absence of a concise theoretical framework. Here, we describe a unified framework that encompasses both contexts. Our work sheds light onto the ongoing debate on whether attention modulates neural response gain, tuning width, and/or preferred feature. We evaluate the framework by conducting simulations for two tasks: (1) classification (discrimination) of two stimuli sa and sb and (2) searching for a target T among distractors D. Results demonstrate that all of gain, tuning, and preferred feature modulation happen to different extents, depending on stimulus conditions and task demands. The theoretical analysis shows that task difficulty (linked to difference Δ between sa and sb, or T, and D) is a crucial factor in optimal modulation, with different effects in discrimination vs. search. Further, our framework allows us to quantify the relative utility of neural parameters. In easy tasks (when Δ is large compared to the density of the neural population), modulating gains and preferred features is sufficient to yield nearly optimal performance; however, in difficult tasks (smaller Δ), modulating tuning width becomes necessary to improve performance. This suggests that the conflicting reports from different experimental studies may be due to differences in tasks and in their difficulties. We further propose future electrophysiology experiments to observe different types of attentional modulation in a same neuron. PMID:24723881
GA-optimization for rapid prototype system demonstration
NASA Technical Reports Server (NTRS)
Kim, Jinwoo; Zeigler, Bernard P.
1994-01-01
An application of the Genetic Algorithm (GA) is discussed. A novel scheme of Hierarchical GA was developed to solve complicated engineering problems which require optimization of a large number of parameters with high precision. High level GAs search for few parameters which are much more sensitive to the system performance. Low level GAs search in more detail and employ a greater number of parameters for further optimization. Therefore, the complexity of the search is decreased and the computing resources are used more efficiently.
NASA Astrophysics Data System (ADS)
Feng, Wen; Yang, Sen
2016-12-01
Thermomechanical processing has an important effect on the grain boundary character distribution. To obtain the optimal thermomechanical processing parameters is the key of grain boundary engineering. In this study, genetic algorithm (GA) based on artificial neural network model was proposed to optimize the thermomechanical processing parameters. In this model, a back-propagation neural network (BPNN) was established to map the relationship between thermomechanical processing parameters and the fraction of low-Σ CSL boundaries, and GA integrated with BPNN (BPNN/GA) was applied to optimize the thermomechanical processing parameters. The validation of the optimal thermomechanical processing parameters was verified by an experiment. Moreover, the microstructures and the intergranular corrosion resistance of the base material (BM) and the materials produced by the optimal thermomechanical processing parameters (termed as the GBEM) were studied. Compared to the BM specimen, the fraction of low-Σ CSL boundaries was increased from 56.8 to 77.9% and the random boundary network was interrupted by the low-Σ CSL boundaries, and the intergranular corrosion resistance was improved in the GBEM specimen. The results indicated that the BPNN/GA model was an effective and reliable means for the thermomechanical processing parameters optimization, which resulted in improving the intergranular corrosion resistance in 304 austenitic stainless steel.
The performance improvement of SRAF placement rules using GA optimization
NASA Astrophysics Data System (ADS)
Xu, Yan; Zhang, Bidan; Wang, Changan; Wilkinson, William; Bolton, John
2016-10-01
In this paper, genetic algorithm (GA) method is applied to both positive and negative Sub Resolution Assist Features (SRAF) insertion rules. Simulation results and wafer data demonstrated that the optimized SRAF rules helped resolve the SRAF printing issues while dramatically improving the process window of the working layer. To find out the best practice to place the SRAF, model-based SRAF (MBSRAF), rule-based SRAF (RBSRAF) with pixelated OPC simulation and RBSRAF with GA method are thoroughly compared. The result shows the apparent advantage of RBSRAF with GA method.
NASA Astrophysics Data System (ADS)
Liu, Yang; Gao, Bo; Gong, Min; Shi, Ruiying
2017-06-01
The influence of a GaN layer as a sub-quantum well for an AlGaN/GaN/AlGaN double barrier resonant tunneling diode (RTD) on device performance has been investigated by means of numerical simulation. The introduction of the GaN layer as the sub-quantum well turns the dominant transport mechanism of RTD from the 3D-2D model to the 2D-2D model and increases the energy difference between tunneling energy levels. It can also lower the effective height of the emitter barrier. Consequently, the peak current and peak-to-valley current difference of RTD have been increased. The optimal GaN sub-quantum well parameters are found through analyzing the electrical performance, energy band, and transmission coefficient of RTD with different widths and depths of the GaN sub-quantum well. The most pronounced electrical parameters, a peak current density of 5800 KA/cm2, a peak-to-valley current difference of 1.466 A, and a peak-to-valley current ratio of 6.35, could be achieved by designing RTD with the active region structure of GaN/Al0.2Ga0.8 N/GaN/Al0.2Ga0.8 N (3 nm/1.5 nm/1.5 nm/1.5 nm).
Long, Yi; Du, Zhi-Jiang; Wang, Wei-Dong; Dong, Wei
2016-01-01
A lower limb assistive exoskeleton is designed to help operators walk or carry payloads. The exoskeleton is required to shadow human motion intent accurately and compliantly to prevent incoordination. If the user's intention is estimated accurately, a precise position control strategy will improve collaboration between the user and the exoskeleton. In this paper, a hybrid position control scheme, combining sliding mode control (SMC) with a cerebellar model articulation controller (CMAC) neural network, is proposed to control the exoskeleton to react appropriately to human motion intent. A genetic algorithm (GA) is utilized to determine the optimal sliding surface and the sliding control law to improve performance of SMC. The proposed control strategy (SMC_GA_CMAC) is compared with three other types of approaches, that is, conventional SMC without optimization, optimal SMC with GA (SMC_GA), and SMC with CMAC compensation (SMC_CMAC), all of which are employed to track the desired joint angular position which is deduced from Clinical Gait Analysis (CGA) data. Position tracking performance is investigated with cosimulation using ADAMS and MATLAB/SIMULINK in two cases, of which the first case is without disturbances while the second case is with a bounded disturbance. The cosimulation results show the effectiveness of the proposed control strategy which can be employed in similar exoskeleton systems.
Long, Yi; Du, Zhi-jiang; Wang, Wei-dong; Dong, Wei
2016-01-01
A lower limb assistive exoskeleton is designed to help operators walk or carry payloads. The exoskeleton is required to shadow human motion intent accurately and compliantly to prevent incoordination. If the user's intention is estimated accurately, a precise position control strategy will improve collaboration between the user and the exoskeleton. In this paper, a hybrid position control scheme, combining sliding mode control (SMC) with a cerebellar model articulation controller (CMAC) neural network, is proposed to control the exoskeleton to react appropriately to human motion intent. A genetic algorithm (GA) is utilized to determine the optimal sliding surface and the sliding control law to improve performance of SMC. The proposed control strategy (SMC_GA_CMAC) is compared with three other types of approaches, that is, conventional SMC without optimization, optimal SMC with GA (SMC_GA), and SMC with CMAC compensation (SMC_CMAC), all of which are employed to track the desired joint angular position which is deduced from Clinical Gait Analysis (CGA) data. Position tracking performance is investigated with cosimulation using ADAMS and MATLAB/SIMULINK in two cases, of which the first case is without disturbances while the second case is with a bounded disturbance. The cosimulation results show the effectiveness of the proposed control strategy which can be employed in similar exoskeleton systems. PMID:27069353
NASA Astrophysics Data System (ADS)
Thompson, D. E.; Rajkumar, T.
2002-12-01
The San Francisco Bay Delta is a large hydrodynamic complex that incorporates the Sacramento and San Joaquin Estuaries, the Suisan Marsh, and the San Francisco Bay proper. Competition exists for the use of this extensive water system both from the fisheries industry, the agricultural industry, and from the marine and estuarine animal species within the Delta. As tidal fluctuations occur, more saline water pushes upstream allowing fish to migrate beyond the Suisan Marsh for breeding and habitat occupation. However, the agriculture industry does not want extensive salinity intrusion to impact water quality for human and plant consumption. The balance is regulated by pumping stations located along the estuaries and reservoirs whereby flushing of fresh water keeps the saline intrusion at bay. The pumping schedule is driven by data collected at various locations within the Bay Delta and by numerical models that predict the salinity intrusion as part of a larger model of the system. The Interagency Ecological Program (IEP) for the San Francisco Bay / Sacramento-San Joaquin Estuary collects, monitors, and archives the data, and the Department of Water Resources provides a numerical model simulation (DSM2) from which predictions are made that drive the pumping schedule. A problem with DSM2 is that the numerical simulation takes roughly 16 hours to complete a prediction. We have created a neural net, optimized with a genetic algorithm, that takes as input the archived data from multiple gauging stations and predicts stage, salinity, and flow at the Carquinez Straits (at the downstream end of the Suisan Marsh). This model seems to be robust in its predictions and operates much faster than the current numerical DSM2 model. Because the Bay-Delta is strongly tidally driven, we used both Principal Component Analysis and Fast Fourier Transforms to discover dominant features within the IEP data. We then filtered out the dominant tidal forcing to discover non-primary tidal effects
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
Optimal input sizes for neural network de-interlacing
NASA Astrophysics Data System (ADS)
Choi, Hyunsoo; Seo, Guiwon; Lee, Chulhee
2009-02-01
Neural network de-interlacing has shown promising results among various de-interlacing methods. In this paper, we investigate the effects of input size for neural networks for various video formats when the neural networks are used for de-interlacing. In particular, we investigate optimal input sizes for CIF, VGA and HD video formats.
High-gain AlGaAs/GaAs double heterojunction Darlington phototransistors for optical neural networks
NASA Technical Reports Server (NTRS)
Kim, Jae H. (Inventor); Lin, Steven H. (Inventor)
1991-01-01
High-gain MOCVD-grown (metal-organic chemical vapor deposition) AlGaAs/GaAs/AlGaAs n-p-n double heterojunction bipolar transistors (DHBTs) and Darlington phototransistor pairs are provided for use in optical neural networks and other optoelectronic integrated circuit applications. The reduced base doping level used results in effective blockage of Zn out-diffusion, enabling a current gain of 500, higher than most previously reported values for Zn-diffused-base DHBTs. Darlington phototransitor pairs of this material can achieve a current gain of over 6000, which satisfies the gain requirement for optical neural network designs, which advantageously may employ neurons comprising the Darlington phototransistor pairs in series with a light source.
Neural network for constrained nonsmooth optimization using Tikhonov regularization.
Qin, Sitian; Fan, Dejun; Wu, Guangxi; Zhao, Lijun
2015-03-01
This paper presents a one-layer neural network to solve nonsmooth convex optimization problems based on the Tikhonov regularization method. Firstly, it is shown that the optimal solution of the original problem can be approximated by the optimal solution of a strongly convex optimization problems. Then, it is proved that for any initial point, the state of the proposed neural network enters the equality feasible region in finite time, and is globally convergent to the unique optimal solution of the related strongly convex optimization problems. Compared with the existing neural networks, the proposed neural network has lower model complexity and does not need penalty parameters. In the end, some numerical examples and application are given to illustrate the effectiveness and improvement of the proposed neural network.
A Projection Neural Network for Constrained Quadratic Minimax Optimization.
Liu, Qingshan; Wang, Jun
2015-11-01
This paper presents a projection neural network described by a dynamic system for solving constrained quadratic minimax programming problems. Sufficient conditions based on a linear matrix inequality are provided for global convergence of the proposed neural network. Compared with some of the existing neural networks for quadratic minimax optimization, the proposed neural network in this paper is capable of solving more general constrained quadratic minimax optimization problems, and the designed neural network does not include any parameter. Moreover, the neural network has lower model complexities, the number of state variables of which is equal to that of the dimension of the optimization problems. The simulation results on numerical examples are discussed to demonstrate the effectiveness and characteristics of the proposed neural network.
Neural networks optimally trained with noisy data
NASA Astrophysics Data System (ADS)
Wong, K. Y. Michael; Sherrington, David
1993-06-01
We study the retrieval behaviors of neural networks which are trained to optimize their performance for an ensemble of noisy example patterns. In particular, we consider (1) the performance overlap, which reflects the performance of the network in an operating condition identical to the training condition; (2) the storage overlap, which reflects the ability of the network to merely memorize the stored information; (3) the attractor overlap, which reflects the precision of retrieval for dilute feedback networks; and (4) the boundary overlap, which defines the boundary of the basin of attraction, and hence the associative ability for dilute feedback networks. We find that for sufficiently low training noise, the network optimizes its overall performance by sacrificing the individual performance of a minority of patterns, resulting in a two-band distribution of the aligning fields. For a narrow range of storage level, the network loses and then regains its retrieval capability when the training noise level increases, and we interpret that this reentrant retrieval behavior is related to competing tendencies in structuring the basins of attraction for the stored patterns. Reentrant behavior is also observed in the space of synaptic interactions, in which the replica symmetric solution of the optimal network destabilizes and then restabilizes when the training noise level increases. We summarize these observations by picturing training noises as an instrument for widening the basins of attractions of the stored patterns at the expense of reducing the precision of retrieval.
RCQ-GA: RDF Chain Query Optimization Using Genetic Algorithms
NASA Astrophysics Data System (ADS)
Hogenboom, Alexander; Milea, Viorel; Frasincar, Flavius; Kaymak, Uzay
The application of Semantic Web technologies in an Electronic Commerce environment implies a need for good support tools. Fast query engines are needed for efficient querying of large amounts of data, usually represented using RDF. We focus on optimizing a special class of SPARQL queries, the so-called RDF chain queries. For this purpose, we devise a genetic algorithm called RCQ-GA that determines the order in which joins need to be performed for an efficient evaluation of RDF chain queries. The approach is benchmarked against a two-phase optimization algorithm, previously proposed in literature. The more complex a query is, the more RCQ-GA outperforms the benchmark in solution quality, execution time needed, and consistency of solution quality. When the algorithms are constrained by a time limit, the overall performance of RCQ-GA compared to the benchmark further improves.
NASA Technical Reports Server (NTRS)
Thompson, David E.; Rajkumar, T.; Clancy, Daniel (Technical Monitor)
2002-01-01
The San Francisco Bay Delta is a large hydrodynamic complex that incorporates the Sacramento and San Joaquin Estuaries, the Burman Marsh, and the San Francisco Bay proper. Competition exists for the use of this extensive water system both from the fisheries industry, the agricultural industry, and from the marine and estuarine animal species within the Delta. As tidal fluctuations occur, more saline water pushes upstream allowing fish to migrate beyond the Burman Marsh for breeding and habitat occupation. However, the agriculture industry does not want extensive salinity intrusion to impact water quality for human and plant consumption. The balance is regulated by pumping stations located alone the estuaries and reservoirs whereby flushing of fresh water keeps the saline intrusion at bay. The pumping schedule is driven by data collected at various locations within the Bay Delta and by numerical models that predict the salinity intrusion as part of a larger model of the system. The Interagency Ecological Program (IEP) for the San Francisco Bay/Sacramento-San Joaquin Estuary collects, monitors, and archives the data, and the Department of Water Resources provides a numerical model simulation (DSM2) from which predictions are made that drive the pumping schedule. A problem with this procedure is that the numerical simulation takes roughly 16 hours to complete a C: prediction. We have created a neural net, optimized with a genetic algorithm, that takes as input the archived data from multiple stations and predicts stage, salinity, and flow at the Carquinez Straits (at the downstream end of the Burman Marsh). This model seems to be robust in its predictions and operates much faster than the current numerical DSM2 model. Because the system is strongly tidal driven, we used both Principal Component Analysis and Fast Fourier Transforms to discover dominant features within the IEP data. We then filtered out the dominant tidal forcing to discover non-primary tidal effects
NASA Technical Reports Server (NTRS)
Thompson, David E.; Rajkumar, T.; Clancy, Daniel (Technical Monitor)
2002-01-01
The San Francisco Bay Delta is a large hydrodynamic complex that incorporates the Sacramento and San Joaquin Estuaries, the Burman Marsh, and the San Francisco Bay proper. Competition exists for the use of this extensive water system both from the fisheries industry, the agricultural industry, and from the marine and estuarine animal species within the Delta. As tidal fluctuations occur, more saline water pushes upstream allowing fish to migrate beyond the Burman Marsh for breeding and habitat occupation. However, the agriculture industry does not want extensive salinity intrusion to impact water quality for human and plant consumption. The balance is regulated by pumping stations located alone the estuaries and reservoirs whereby flushing of fresh water keeps the saline intrusion at bay. The pumping schedule is driven by data collected at various locations within the Bay Delta and by numerical models that predict the salinity intrusion as part of a larger model of the system. The Interagency Ecological Program (IEP) for the San Francisco Bay/Sacramento-San Joaquin Estuary collects, monitors, and archives the data, and the Department of Water Resources provides a numerical model simulation (DSM2) from which predictions are made that drive the pumping schedule. A problem with this procedure is that the numerical simulation takes roughly 16 hours to complete a C: prediction. We have created a neural net, optimized with a genetic algorithm, that takes as input the archived data from multiple stations and predicts stage, salinity, and flow at the Carquinez Straits (at the downstream end of the Burman Marsh). This model seems to be robust in its predictions and operates much faster than the current numerical DSM2 model. Because the system is strongly tidal driven, we used both Principal Component Analysis and Fast Fourier Transforms to discover dominant features within the IEP data. We then filtered out the dominant tidal forcing to discover non-primary tidal effects
Lu, Zhenming; He, Zhe; Xu, Hongyu; Shi, Jinsong; Xu, Zhenghong
2011-12-01
To illustrate the complex fermentation process of submerged culture of Antrodia camphorata ATCC 200183, we observed the morphology change of this filamentous fungus. Then we used two optimization models namely response surface methodology (RSM) and artificial neural network (ANN) to model the fermentation process of Antrodia camphorata. By genetic algorithm (GA), we optimized the inoculum size and medium components for Antrodia camphorata production. The results show that fitness and prediction accuracy of ANN model was higher when compared to those of RSM model. Using GA, we optimized the input space of ANN model, and obtained maximum biomass of 6.2 g/L at the GA-optimized concentrations of spore (1.76x 10(5) /mL) and medium components (glucose, 29.1 g/L; peptone, 9.3 g/L; and soybean flour, 2.8 g/L). The biomass obtained using the ANN-GA designed medium was (6.1+/-0.2) g/L which was in good agreement with the predicted value. The same optimization process may be used to improve the production of mycelia and bioactive metabolites from potent medicinal fungi by changing the fermentation parameters.
Genetic algorithm for the optimization of features and neural networks in ECG signals classification
Li, Hongqiang; Yuan, Danyang; Ma, Xiangdong; Cui, Dianyin; Cao, Lu
2017-01-01
Feature extraction and classification of electrocardiogram (ECG) signals are necessary for the automatic diagnosis of cardiac diseases. In this study, a novel method based on genetic algorithm-back propagation neural network (GA-BPNN) for classifying ECG signals with feature extraction using wavelet packet decomposition (WPD) is proposed. WPD combined with the statistical method is utilized to extract the effective features of ECG signals. The statistical features of the wavelet packet coefficients are calculated as the feature sets. GA is employed to decrease the dimensions of the feature sets and to optimize the weights and biases of the back propagation neural network (BPNN). Thereafter, the optimized BPNN classifier is applied to classify six types of ECG signals. In addition, an experimental platform is constructed for ECG signal acquisition to supply the ECG data for verifying the effectiveness of the proposed method. The GA-BPNN method with the MIT-BIH arrhythmia database achieved a dimension reduction of nearly 50% and produced good classification results with an accuracy of 97.78%. The experimental results based on the established acquisition platform indicated that the GA-BPNN method achieved a high classification accuracy of 99.33% and could be efficiently applied in the automatic identification of cardiac arrhythmias. PMID:28139677
Genetic algorithm for the optimization of features and neural networks in ECG signals classification
NASA Astrophysics Data System (ADS)
Li, Hongqiang; Yuan, Danyang; Ma, Xiangdong; Cui, Dianyin; Cao, Lu
2017-01-01
Feature extraction and classification of electrocardiogram (ECG) signals are necessary for the automatic diagnosis of cardiac diseases. In this study, a novel method based on genetic algorithm-back propagation neural network (GA-BPNN) for classifying ECG signals with feature extraction using wavelet packet decomposition (WPD) is proposed. WPD combined with the statistical method is utilized to extract the effective features of ECG signals. The statistical features of the wavelet packet coefficients are calculated as the feature sets. GA is employed to decrease the dimensions of the feature sets and to optimize the weights and biases of the back propagation neural network (BPNN). Thereafter, the optimized BPNN classifier is applied to classify six types of ECG signals. In addition, an experimental platform is constructed for ECG signal acquisition to supply the ECG data for verifying the effectiveness of the proposed method. The GA-BPNN method with the MIT-BIH arrhythmia database achieved a dimension reduction of nearly 50% and produced good classification results with an accuracy of 97.78%. The experimental results based on the established acquisition platform indicated that the GA-BPNN method achieved a high classification accuracy of 99.33% and could be efficiently applied in the automatic identification of cardiac arrhythmias.
Optimization Principles for the Neural Code
NASA Astrophysics Data System (ADS)
Deweese, Michael Robert
1995-01-01
Animals receive information from the world in the form of continuous functions of time. At a very early stage in processing, however, these continuous signals are converted into discrete sequences of identical "spikes". All information that the brain receives about the outside world is encoded in the arrival times of these spikes. The goal of this thesis is to determine if there is a universal principle at work in this neural code. We are motivated by several recent experiments on a wide range of sensory systems which share four main features: High information rates, moderate signal to noise ratio, efficient use of the spike train entropy to encode the signal, and the ability to extract nearly all the information encoded in the spike train with a linear response function triggered by the spikes. We propose that these features can be understood in terms of codes "designed" to maximize information flow. To test this idea, we use the fact that any point process encoding of an analog signal embedded in noise can be written in the language of a threshold crossing model to develop a systematic expansion for the transmitted information about the Poisson limit--the limit where there are no correlations between the spikes. All codes take the same simple form in the Poisson limit, and all of the seemingly unrelated features of the data arise naturally when we optimize a simple linear filtered threshold crossing model. We make a new prediction: Finding the optimum requires adaptation to the statistical structure of the signal and noise, not just to DC offsets. The only disagreement we find is that real neurons outperform our model in the task it was optimized for--they transmit much more information. We then place an upper bound on the amount of information available from the leading term in the Poisson expansion for any possible encoding, and find that real neurons do exceedingly well even by this standard. We conclude that several important features of the neural code can
High-resistivity GaN buffer templates and their optimization for GaN-based HFETs
NASA Astrophysics Data System (ADS)
Hubbard, S. M.; Zhao, G.; Pavlidis, D.; Sutton, W.; Cho, E.
2005-11-01
High-resistance (HR) GaN templates for AlGaN/GaN heterojunction field effect transistor (HFET) applications were grown using organometallic vapor phase epitaxy. The GaN sheet resistance was tuned using final nucleation layer (NL) annealing temperature and NL thickness. Using an annealing temperature of 1033 °C and NL thickness of 26 nm, GaN with sheet resistance of 10 10 Ω/sq was achieved, comparable to that of Fe-doped GaN. Material characterization results show that the high-resistance GaN is achieved due to compensating acceptor levels that may be introduced through edge-type threading dislocations. Optimization of annealing temperature and NL thickness provided a means to maximize GaN sheet resistance without significantly degrading material quality. In situ laser reflectance was used to correlate the NL properties to sheet resistance and material quality, providing a figure of merit for expected sheet resistance. AlGaN/GaN HFET layers grown using HR GaN templates with R of 10 10 Ω/sq gave surface and interface roughness of 14 and 7 Å, respectively. The 2DEG Hall mobility and sheet charge of HFETs grown using HR GaN templates was comparable to similar layers grown using unintentionally doped (UID) GaN templates.
Neural Meta-Memes Framework for Combinatorial Optimization
NASA Astrophysics Data System (ADS)
Song, Li Qin; Lim, Meng Hiot; Ong, Yew Soon
In this paper, we present a Neural Meta-Memes Framework (NMMF) for combinatorial optimization. NMMF is a framework which models basic optimization algorithms as memes and manages them dynamically when solving combinatorial problems. NMMF encompasses neural networks which serve as the overall planner/coordinator to balance the workload between memes. We show the efficacy of the proposed NMMF through empirical study on a class of combinatorial problem, the quadratic assignment problem (QAP).
Genetic algorithm for neural networks optimization
NASA Astrophysics Data System (ADS)
Setyawati, Bina R.; Creese, Robert C.; Sahirman, Sidharta
2004-11-01
This paper examines the forecasting performance of multi-layer feed forward neural networks in modeling a particular foreign exchange rates, i.e. Japanese Yen/US Dollar. The effects of two learning methods, Back Propagation and Genetic Algorithm, in which the neural network topology and other parameters fixed, were investigated. The early results indicate that the application of this hybrid system seems to be well suited for the forecasting of foreign exchange rates. The Neural Networks and Genetic Algorithm were programmed using MATLAB«.
Strain relief and growth optimization of GaSb on GaP by molecular beam epitaxy.
Wang, Y; Ruterana, P; Chen, J; Desplanque, L; El Kazzi, S; Wallart, X
2012-08-22
In this paper, the impact of growth parameters on the strain relaxation of highly lattice mismatched (11.8%) GaSb grown on GaP substrate by molecular beam epitaxy has been investigated. The surface morphology, misfit dislocation and strain relaxation of the GaSb islands are shown to be highly related to the initial surface treatment, growth rate and temperature. More specifically, Sb-rich surface treatment is shown to promote the formation of Lomer misfit dislocations. Analysis of the misfit dislocation and strain relaxation as functions of the growth temperature and rate led to an optimal growth window for a high quality GaSb epitaxial layer on (001) GaP. With this demonstrated optimized growth, a high mobility (25,500 cm(2) V (-1) s(-1) at room temperature) AlSb/InAs heterostructure on a semi-insulating (001) GaP substrate has been achieved.
Optimal neural computations require analog processors
Beiu, V.
1998-12-31
This paper discusses some of the limitations of hardware implementations of neural networks. The authors start by presenting neural structures and their biological inspirations, while mentioning the simplifications leading to artificial neural networks. Further, the focus will be on hardware imposed constraints. They will present recent results for three different alternatives of parallel implementations of neural networks: digital circuits, threshold gate circuits, and analog circuits. The area and the delay will be related to the neurons` fan-in and to the precision of their synaptic weights. The main conclusion is that hardware-efficient solutions require analog computations, and suggests the following two alternatives: (i) cope with the limitations imposed by silicon, by speeding up the computation of the elementary silicon neurons; (2) investigate solutions which would allow the use of the third dimension (e.g. using optical interconnections).
Neural network based decomposition in optimal structural synthesis
NASA Technical Reports Server (NTRS)
Hajela, P.; Berke, L.
1992-01-01
The present paper describes potential applications of neural networks in the multilevel decomposition based optimal design of structural systems. The generic structural optimization problem of interest, if handled as a single problem, results in a large dimensionality problem. Decomposition strategies allow for this problem to be represented by a set of smaller, decoupled problems, for which solutions may either be obtained with greater ease or may be obtained in parallel. Neural network models derived through supervised training, are used in two distinct modes in this work. The first uses neural networks to make available efficient analysis models for use in repetitive function evaluations as required by the optimization algorithm. In the second mode, neural networks are used to represent the coupling that exists between the decomposed subproblems. The approach is illustrated by application to the multilevel decomposition-based synthesis of representative truss and frame structures.
Genetic Algorithm (GA)-Based Inclinometer Layout Optimization
Liang, Weijie; Zhang, Ping; Chen, Xianping; Cai, Miao; Yang, Daoguo
2015-01-01
This paper presents numerical simulation results of an airflow inclinometer with sensitivity studies and thermal optimization of the printed circuit board (PCB) layout for an airflow inclinometer based on a genetic algorithm (GA). Due to the working principle of the gas sensor, the changes of the ambient temperature may cause dramatic voltage drifts of sensors. Therefore, eliminating the influence of the external environment for the airflow is essential for the performance and reliability of an airflow inclinometer. In this paper, the mechanism of an airflow inclinometer and the influence of different ambient temperatures on the sensitivity of the inclinometer will be examined by the ANSYS-FLOTRAN CFD program. The results show that with changes of the ambient temperature on the sensing element, the sensitivity of the airflow inclinometer is inversely proportional to the ambient temperature and decreases when the ambient temperature increases. GA is used to optimize the PCB thermal layout of the inclinometer. The finite-element simulation method (ANSYS) is introduced to simulate and verify the results of our optimal thermal layout, and the results indicate that the optimal PCB layout greatly improves (by more than 50%) the sensitivity of the inclinometer. The study may be useful in the design of PCB layouts that are related to sensitivity improvement of gas sensors. PMID:25897500
Genetic Algorithm (GA)-Based Inclinometer Layout Optimization.
Liang, Weijie; Zhang, Ping; Chen, Xianping; Cai, Miao; Yang, Daoguo
2015-04-17
This paper presents numerical simulation results of an airflow inclinometer with sensitivity studies and thermal optimization of the printed circuit board (PCB) layout for an airflow inclinometer based on a genetic algorithm (GA). Due to the working principle of the gas sensor, the changes of the ambient temperature may cause dramatic voltage drifts of sensors. Therefore, eliminating the influence of the external environment for the airflow is essential for the performance and reliability of an airflow inclinometer. In this paper, the mechanism of an airflow inclinometer and the influence of different ambient temperatures on the sensitivity of the inclinometer will be examined by the ANSYS-FLOTRAN CFD program. The results show that with changes of the ambient temperature on the sensing element, the sensitivity of the airflow inclinometer is inversely proportional to the ambient temperature and decreases when the ambient temperature increases. GA is used to optimize the PCB thermal layout of the inclinometer. The finite-element simulation method (ANSYS) is introduced to simulate and verify the results of our optimal thermal layout, and the results indicate that the optimal PCB layout greatly improves (by more than 50%) the sensitivity of the inclinometer. The study may be useful in the design of PCB layouts that are related to sensitivity improvement of gas sensors.
Neural networks for the optimization of crude oil blending.
Yu, Wen; Morales, América
2005-10-01
Crude oil blending is an important unit in petroleum refining industry. Many blend automation systems use real-time optimizer (RTO), which apply current process information to update the model and predict the optimal operating policy. The key unites of the conventional RTO are on-line analyzers. Sometimes oil fields cannot apply these analyzers. In this paper, we propose an off-line optimization technique to overcome the main drawback of RTO. We use the history data to approximate the output of the on-line analyzers, then the desired optimal inlet flow rates are calculated by the optimization technique. After this off-line optimization, the inlet flow rates are used for on-line control, for example PID control, which forces the flow rate to follow the desired inlet flow rates. Neural networks are applied to model the blending process from the history data. The new optimization is carried out via the neural model. The contributions of this paper are: (1) Stable learning for the discrete-time multilayer neural network is proposed. (2) Sensitivity analysis of the neural optimization is given. (3) Real data of a oil field is used to show effectiveness of the proposed method.
Neural dynamic optimization for control systems. I. Background.
Seong, C Y; Widrow, B
2001-01-01
The paper presents neural dynamic optimization (NDO) as a method of optimal feedback control for nonlinear multi-input-multi-output (MIMO) systems. The main feature of NDO is that it enables neural networks to approximate the optimal feedback solution whose existence dynamic programming (DP) justifies, thereby reducing the complexities of computation and storage problems of the classical methods such as DP. This paper mainly describes the background and motivations for the development of NDO, while the two other subsequent papers of this topic present the theory of NDO and demonstrate the method with several applications including control of autonomous vehicles and of a robot arm, respectively.
Neural dynamic optimization for control systems.II. Theory.
Seong, C Y; Widrow, B
2001-01-01
The paper presents neural dynamic optimization (NDO) as a method of optimal feedback control for nonlinear multi-input-multi-output (MIMO) systems. The main feature of NDO is that it enables neural networks to approximate the optimal feedback solution whose existence dynamic programming (DP) justifies, thereby reducing the complexities of computation and storage problems of the classical methods such as DP. This paper mainly describes the theory of NDO, while the two other companion papers of this topic explain the background for the development of NDO and demonstrate the method with several applications including control of autonomous vehicles and of a robot arm, respectively.
Theoretical study on optimization of high efficiency GaInP/GaInAs/Ge tandem solar cells
NASA Astrophysics Data System (ADS)
Lin, Gui Jiang; Huang, Sheng Rong; Wu, Jyh Chiarng; Huang, Mei Chun
2009-08-01
This paper investigates which dopping concentration or layer thickness should be used to design practical GaInP/GaInAs/Ge triple-junction cells in order to optimize their performance. A rigorous model includes optical and electrical modules is developed to simulate the external quantumn efficiency, photocurrent and photovoltage of the GaInP/GaInAs/Ge tandem solar cells. It is found that cell efficiency strongly dependend on the top cell thickness and doping concentration at base and emitter layers. Proper structures of the tandem cell operating under AM0 ("air mass zero") illumination are suggested to obtain high efficiency.
Optimal groundwater remediation using artificial neural networks and the genetic algorithm
Rogers, Leah L.
1992-08-01
An innovative computational approach for the optimization of groundwater remediation is presented which uses artificial neural networks (ANNs) and the genetic algorithm (GA). In this approach, the ANN is trained to predict an aspect of the outcome of a flow and transport simulation. Then the GA searches through realizations or patterns of pumping and uses the trained network to predict the outcome of the realizations. This approach has advantages of parallel processing of the groundwater simulations and the ability to ``recycle`` or reuse the base of knowledge formed by these simulations. These advantages offer reduction of computational burden of the groundwater simulations relative to a more conventional approach which uses nonlinear programming (NLP) with a quasi-newtonian search. Also the modular nature of this approach facilitates substitution of different groundwater simulation models.
NASA Astrophysics Data System (ADS)
Soh, C. B.; Hartono, H.; Chow, S. Y.; Chua, S. J.; Fitzgerald, E. A.
2007-01-01
Nanoporous GaN template has been fabricated by electrochemical etching to give hexagonal pits with nanoscale pores of size 20-50nm in the underlying grains. The effect of GaN buffer layer grown at various temperatures from 650to1015°C on these as-fabricated nanopores templates is investigated by transmission electron microscopy. The buffer layer grown at the optimized temperature of 850°C partially fill up the pores and voids with annihilation of threading dislocations, serving as an excellent template for high-quality GaN growth. This phenomenon is, however, not observed for the samples grown with other temperature buffer layers. Micro-Raman measurements show significant strain relaxation and improvement in the crystal quality of the overgrown GaN layer on nanoporous GaN template as compared to overgrown on conventional GaN template.
Optimizing GaInN/GaN light-emitting diode structures under piezoelectric polarization
NASA Astrophysics Data System (ADS)
Elsaesser, David R.; Durniak, Mark T.; Bross, Adam S.; Wetzel, Christian
2017-09-01
We model and optimize various light emitting diode structures under bias voltage to maximize emission efficiency with particular respect to piezoelectric polarization. We compare polar and non-polar structures, namely, wurtzite c-plane, a-plane, (11-22) semi-polar, and (001) cubic crystal orientations in self-consistent Schrödinger-Poisson and drift-diffusion models. We consider both structures strained to a GaN pn-junction and strain-reduced systems based on GaInN templates. In light of numerous experimental findings of the actual electric field strength, we find it necessary to reduce the piezoelectric coefficients over those commonly cited. A weaker variation with composition or wavelength is the consequence. For the non-polar and cubic systems, we find a 22% increase of the electron-hole overlap and an 18% increase for the c-plane strain-reduced system at an InN fraction of x = 0.30 when compared to standard c-plane structures. For the green and longer wavelength range, we find that strain-reduced and cubic GaN systems should hold particular promise for higher radiative efficiency.
An Evolutionary Optimization Framework for Neural Networks and Neuromorphic Architectures
Schuman, Catherine D; Plank, James; Disney, Adam; Reynolds, John
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.
Toward Optimal Target Placement for Neural Prosthetic Devices
Cunningham, John P.; Yu, Byron M.; Gilja, Vikash; Ryu, Stephen I.; Shenoy, Krishna V.
2008-01-01
Neural prosthetic systems have been designed to estimate continuous reach trajectories (motor prostheses) and to predict discrete reach targets (communication prostheses). In the latter case, reach targets are typically decoded from neural spiking activity during an instructed delay period before the reach begins. Such systems use targets placed in radially symmetric geometries independent of the tuning properties of the neurons available. Here we seek to automate the target placement process and increase decode accuracy in communication prostheses by selecting target locations based on the neural population at hand. Motor prostheses that incorporate intended target information could also benefit from this consideration. We present an optimal target placement algorithm that approximately maximizes decode accuracy with respect to target locations. In simulated neural spiking data fit from two monkeys, the optimal target placement algorithm yielded statistically significant improvements up to 8 and 9% for two and sixteen targets, respectively. For four and eight targets, gains were more modest, as the target layouts found by the algorithm closely resembled the canonical layouts. We trained a monkey in this paradigm and tested the algorithm with experimental neural data to confirm some of the results found in simulation. In all, the algorithm can serve not only to create new target layouts that outperform canonical layouts, but it can also confirm or help select among multiple canonical layouts. The optimal target placement algorithm developed here is the first algorithm of its kind, and it should both improve decode accuracy and help automate target placement for neural prostheses. PMID:18829845
SFC Optimization for Aero Engine Based on Hybrid GA-SQP Method
NASA Astrophysics Data System (ADS)
Li, Jie; Fan, Ding; Sreeram, Victor
2013-12-01
This study focuses on on-line specific fuel consumption (SFC) optimization of aero engines. For solving this optimization problem, a nonlinear pneumatic and thermodynamics model of the aero engine is built and a hybrid optimization technique which is formed by combining the genetic algorithm (GA) and the sequential quadratic programming (SQP) is presented. The ability of standard GA and standard SQP in solving this type of problem is investigated. It has been found that, although the SQP is fast, very little SFC reductions can be obtained. The GA is able to solve the problem well but a lot of computational time is needed. The presented hybrid GA-SQP gives a good SFC optimization effect and saves 76.6% computational time when compared to the standard GA. It has been shown that the hybrid GA-SQP is a more effective and higher real-time method for SFC on-line optimization of the aero engine.
On limited fan-in optimal neural networks
Beiu, V.; Makaruk, H.E.; Draghici, S.
1998-03-01
Because VLSI implementations do not cope well with highly interconnected nets the area of a chip growing as the cube of the fan-in--this paper analyses the influence of limited fan in on the size and VLSI optimality of such nets. Two different approaches will show that VLSI- and size-optimal discrete neural networks can be obtained for small (i.e. lower than linear) fan-in values. They have applications to hardware implementations of neural networks. The first approach is based on implementing a certain sub class of Boolean functions, IF{sub n,m} functions. The authors will show that this class of functions can be implemented in VLSI optimal (i.e., minimizing AT{sup 2}) neural networks of small constant fan ins. The second approach is based on implementing Boolean functions for which the classical Shannon`s decomposition can be used. Such a solution has already been used to prove bounds on neural networks with fan-ins limited to 2. They generalize the result presented there to arbitrary fan-in, and prove that the size is minimized by small fan in values, while relative minimum size solutions can be obtained for fan-ins strictly lower than linear. Finally, a size-optimal neural network having small constant fan-ins will be suggested for IF{sub n,m} functions.
Adaptive Optimization of Aircraft Engine Performance Using Neural Networks
NASA Technical Reports Server (NTRS)
Simon, Donald L.; Long, Theresa W.
1995-01-01
Preliminary results are presented on the development of an adaptive neural network based control algorithm to enhance aircraft engine performance. This work builds upon a previous National Aeronautics and Space Administration (NASA) effort known as Performance Seeking Control (PSC). PSC is an adaptive control algorithm which contains a model of the aircraft's propulsion system which is updated on-line to match the operation of the aircraft's actual propulsion system. Information from the on-line model is used to adapt the control system during flight to allow optimal operation of the aircraft's propulsion system (inlet, engine, and nozzle) to improve aircraft engine performance without compromising reliability or operability. Performance Seeking Control has been shown to yield reductions in fuel flow, increases in thrust, and reductions in engine fan turbine inlet temperature. The neural network based adaptive control, like PSC, will contain a model of the propulsion system which will be used to calculate optimal control commands on-line. Hopes are that it will be able to provide some additional benefits above and beyond those of PSC. The PSC algorithm is computationally intensive, it is valid only at near steady-state flight conditions, and it has no way to adapt or learn on-line. These issues are being addressed in the development of the optimal neural controller. Specialized neural network processing hardware is being developed to run the software, the algorithm will be valid at steady-state and transient conditions, and will take advantage of the on-line learning capability of neural networks. Future plans include testing the neural network software and hardware prototype against an aircraft engine simulation. In this paper, the proposed neural network software and hardware is described and preliminary neural network training results are presented.
NASA Astrophysics Data System (ADS)
Jokar, Ali; Godarzi, Ali Abbasi; Saber, Mohammad; Shafii, Mohammad Behshad
2016-11-01
In this paper, a novel approach has been presented to simulate and optimize the pulsating heat pipes (PHPs). The used pulsating heat pipe setup was designed and constructed for this study. Due to the lack of a general mathematical model for exact analysis of the PHPs, a method has been applied for simulation and optimization using the natural algorithms. In this way, the simulator consists of a kind of multilayer perceptron neural network, which is trained by experimental results obtained from our PHP setup. The results show that the complex behavior of PHPs can be successfully described by the non-linear structure of this simulator. The input variables of the neural network are input heat flux to evaporator (q″), filling ratio (FR) and inclined angle (IA) and its output is thermal resistance of PHP. Finally, based upon the simulation results and considering the heat pipe's operating constraints, the optimum operating point of the system is obtained by using genetic algorithm (GA). The experimental results show that the optimum FR (38.25 %), input heat flux to evaporator (39.93 W) and IA (55°) that obtained from GA are acceptable.
Moghri, Mehdi; Omidi, Mostafa; Farahnakian, Masoud
2014-01-01
During the past decade, polymer nanocomposites attracted considerable investment in research and development worldwide. One of the key factors that affect the quality of polymer nanocomposite products in machining is surface roughness. To obtain high quality products and reduce machining costs it is very important to determine the optimal machining conditions so as to achieve enhanced machining performance. The objective of this paper is to develop a predictive model using a combined design of experiments and artificial intelligence approach for optimization of surface roughness in milling of polyamide-6 (PA-6) nanocomposites. A surface roughness predictive model was developed in terms of milling parameters (spindle speed and feed rate) and nanoclay (NC) content using artificial neural network (ANN). As the present study deals with relatively small number of data obtained from full factorial design, application of genetic algorithm (GA) for ANN training is thought to be an appropriate approach for the purpose of developing accurate and robust ANN model. In the optimization phase, a GA is considered in conjunction with the explicit nonlinear function derived from the ANN to determine the optimal milling parameters for minimization of surface roughness for each PA-6 nanocomposite. PMID:24578636
Moghri, Mehdi; Madic, Milos; Omidi, Mostafa; Farahnakian, Masoud
2014-01-01
During the past decade, polymer nanocomposites attracted considerable investment in research and development worldwide. One of the key factors that affect the quality of polymer nanocomposite products in machining is surface roughness. To obtain high quality products and reduce machining costs it is very important to determine the optimal machining conditions so as to achieve enhanced machining performance. The objective of this paper is to develop a predictive model using a combined design of experiments and artificial intelligence approach for optimization of surface roughness in milling of polyamide-6 (PA-6) nanocomposites. A surface roughness predictive model was developed in terms of milling parameters (spindle speed and feed rate) and nanoclay (NC) content using artificial neural network (ANN). As the present study deals with relatively small number of data obtained from full factorial design, application of genetic algorithm (GA) for ANN training is thought to be an appropriate approach for the purpose of developing accurate and robust ANN model. In the optimization phase, a GA is considered in conjunction with the explicit nonlinear function derived from the ANN to determine the optimal milling parameters for minimization of surface roughness for each PA-6 nanocomposite.
Tian, H; Liu, C; Gao, X D; Yao, W B
2013-03-01
Granulocyte colony-stimulating factor (G-CSF) is a cytokine widely used in cancer patients receiving high doses of chemotherapeutic drugs to prevent the chemotherapy-induced suppression of white blood cells. The production of recombinant G-CSF should be increased to meet the increasing market demand. This study aims to model and optimize the carbon source of auto-induction medium to enhance G-CSF production using artificial neural networks coupled with genetic algorithm. In this approach, artificial neural networks served as bioprocess modeling tools, and genetic algorithm (GA) was applied to optimize the established artificial neural network models. Two artificial neural network models were constructed: the back-propagation (BP) network and the radial basis function (RBF) network. The root mean square error, coefficient of determination, and standard error of prediction of the BP model were 0.0375, 0.959, and 8.49 %, respectively, whereas those of the RBF model were 0.0257, 0.980, and 5.82 %, respectively. These values indicated that the RBF model possessed higher fitness and prediction accuracy than the BP model. Under the optimized auto-induction medium, the predicted maximum G-CSF yield by the BP-GA approach was 71.66 %, whereas that by the RBF-GA approach was 75.17 %. These predicted values are in agreement with the experimental results, with 72.4 and 76.014 % for the BP-GA and RBF-GA models, respectively. These results suggest that RBF-GA is superior to BP-GA. The developed approach in this study may be helpful in modeling and optimizing other multivariable, non-linear, and time-variant bioprocesses.
The Neural Basis of Optimism and Pessimism
2013-01-01
Our survival and wellness require a balance between optimism and pessimism. Undue pessimism makes life miserable; however, excessive optimism can lead to dangerously risky behaviors. A review and synthesis of the literature on the neurophysiology subserving these two worldviews suggests that optimism and pessimism are differentially associated with the two cerebral hemispheres. High self-esteem, a cheerful attitude that tends to look at the positive aspects of a given situation, as well as an optimistic belief in a bright future are associated with physiological activity in the left-hemisphere (LH). In contrast, a gloomy viewpoint, an inclination to focus on the negative part and exaggerate its significance, low self-esteem as well as a pessimistic view on what the future holds are interlinked with neurophysiological processes in the right-hemisphere (RH). This hemispheric asymmetry in mediating optimistic and pessimistic outlooks is rooted in several biological and functional differences between the two hemispheres. The RH mediation of a watchful and inhibitive mode weaves a sense of insecurity that generates and supports pessimistic thought patterns. Conversely, the LH mediation of an active mode and the positive feedback it receives through its motor dexterity breed a sense of confidence in one's ability to manage life's challenges, and optimism about the future. PMID:24167413
The neural basis of optimism and pessimism.
Hecht, David
2013-09-01
Our survival and wellness require a balance between optimism and pessimism. Undue pessimism makes life miserable; however, excessive optimism can lead to dangerously risky behaviors. A review and synthesis of the literature on the neurophysiology subserving these two worldviews suggests that optimism and pessimism are differentially associated with the two cerebral hemispheres. High self-esteem, a cheerful attitude that tends to look at the positive aspects of a given situation, as well as an optimistic belief in a bright future are associated with physiological activity in the left-hemisphere (LH). In contrast, a gloomy viewpoint, an inclination to focus on the negative part and exaggerate its significance, low self-esteem as well as a pessimistic view on what the future holds are interlinked with neurophysiological processes in the right-hemisphere (RH). This hemispheric asymmetry in mediating optimistic and pessimistic outlooks is rooted in several biological and functional differences between the two hemispheres. The RH mediation of a watchful and inhibitive mode weaves a sense of insecurity that generates and supports pessimistic thought patterns. Conversely, the LH mediation of an active mode and the positive feedback it receives through its motor dexterity breed a sense of confidence in one's ability to manage life's challenges, and optimism about the future.
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.
Zhukov, A. E.; Asryan, L. V.; Semenova, E. S.; Zubov, F. I.; Kryzhanovskaya, N. V.; Maximov, M. V.
2015-07-15
Band offsets at the heterointerface are calculated for various combinations of InAlGaAs/AlGaAs heteropairs that can be synthesized on GaAs substrates in the layer-by-layer pseudomorphic growth mode. Patterns which make it possible to obtain an asymmetric barrier layer providing the almost obstruction-free transport of holes and the highest possible barrier height for electrons are found. The optimal compositions of both compounds (In{sup 0.232}Al{sup 0.594}Ga{sup 0.174}As/Al{sup 0.355}Ga{sup 0.645}As) at which the flux of electrons across the barrier is at a minimum are determined with consideration for the critical thickness of the indium-containing quaternary solid solution.
Neural dynamic optimization for control systems.III. Applications.
Seong, C Y; Widrow, B
2001-01-01
For pt.II. see ibid., p. 490-501. The paper presents neural dynamic optimization (NDO) as a method of optimal feedback control for nonlinear multi-input-multi-output (MIMO) systems. The main feature of NDO is that it enables neural networks to approximate the optimal feedback solution whose existence dynamic programming (DP) justifies, thereby reducing the complexities of computation and storage problems of the classical methods such as DP. This paper demonstrates NDO with several applications including control of autonomous vehicles and of a robot-arm, while the two other companion papers of this topic describes the background for the development of NDO and present the theory of the method, respectively.
Qiu, Mingyue; Song, Yu
2016-01-01
In the business sector, it has always been a difficult task to predict the exact daily price of the stock market index; hence, there is a great deal of research being conducted regarding the prediction of the direction of stock price index movement. Many factors such as political events, general economic conditions, and traders' expectations may have an influence on the stock market index. There are numerous research studies that use similar indicators to forecast the direction of the stock market index. In this study, we compare two basic types of input variables to predict the direction of the daily stock market index. The main contribution of this study is the ability to predict the direction of the next day's price of the Japanese stock market index by using an optimized artificial neural network (ANN) model. To improve the prediction accuracy of the trend of the stock market index in the future, we optimize the ANN model using genetic algorithms (GA). We demonstrate and verify the predictability of stock price direction by using the hybrid GA-ANN model and then compare the performance with prior studies. Empirical results show that the Type 2 input variables can generate a higher forecast accuracy and that it is possible to enhance the performance of the optimized ANN model by selecting input variables appropriately.
Qiu, Mingyue; Song, Yu
2016-01-01
In the business sector, it has always been a difficult task to predict the exact daily price of the stock market index; hence, there is a great deal of research being conducted regarding the prediction of the direction of stock price index movement. Many factors such as political events, general economic conditions, and traders’ expectations may have an influence on the stock market index. There are numerous research studies that use similar indicators to forecast the direction of the stock market index. In this study, we compare two basic types of input variables to predict the direction of the daily stock market index. The main contribution of this study is the ability to predict the direction of the next day’s price of the Japanese stock market index by using an optimized artificial neural network (ANN) model. To improve the prediction accuracy of the trend of the stock market index in the future, we optimize the ANN model using genetic algorithms (GA). We demonstrate and verify the predictability of stock price direction by using the hybrid GA-ANN model and then compare the performance with prior studies. Empirical results show that the Type 2 input variables can generate a higher forecast accuracy and that it is possible to enhance the performance of the optimized ANN model by selecting input variables appropriately. PMID:27196055
Simple Neural Networks that Optimize Decisions
NASA Astrophysics Data System (ADS)
Brown, Eric; Gao, Juan; Holmes, Philip; Bogacz, Rafal; Gilzenrat, Mark; Cohen, Jonathan D.
We review simple connectionist and firing rate models for mutually inhibiting pools of neurons that discriminate between pairs of stimuli. Both are two-dimensional nonlinear stochastic ordinary differential equations, and although they differ in how inputs and stimuli enter, we show that they are equivalent under state variable and parameter coordinate changes. A key parameter is gain: the maximum slope of the sigmoidal activation function. We develop piecewise-linear and purely linear models, and one-dimensional reductions to Ornstein-Uhlenbeck processes that can be viewed as linear filters, and show that reaction time and error rate statistics are well approximated by these simpler models. We then pose and solve the optimal gain problem for the Ornstein-Uhlenbeck processes, finding explicit gain schedules that minimize error rates for time-varying stimuli. We relate these to time courses of norepinephrine release in cortical areas, and argue that transient firing rate changes in the brainstem nucleus locus coeruleus may be responsible for approximate gain optimization.
Heterostructure design optimization for laser cooling of GaAs
NASA Astrophysics Data System (ADS)
Imangholi, B.; Wang, C.; Soto, E.; Sheik-Bahae, M.; Stintz, A.; Malloy, K.; Nuntawong, N.; Epstein, R.
2007-02-01
Doping of the clad layers in thin GaAs/GaInP heterostructures, displaces the band energy discontinuity, modifies the carrier concentration in the active GaAs region and changes the quality of the hetero-interfaces. As a result, internal and consequently external quantum efficiencies in the double heterostructure are affected. In this paper, the interfacial quality of GaAs/GaInP heterostructure is systematically investigated by adjusting the doping level and type (n or p) of the cladding layer. An optimum structure for laser cooling applications is proposed.
Pulsed irradiation of optimized, MBE grown, AlGaAs/GaAs radiation hardened photodiodes. Rev
Wiczer, J.J.; Fischer, T.A.; Dawson, L.R.; Osbourn, G.C.; Zipperian, T.E.; Barnes, C.E.
1984-01-01
An AlGaAs/GaAs double heterojunction, mesa isolated, photodiode grown by molecular beam epitaxy was irradiated with 18 MeV electrons, 1 to 10 MeV x-rays, and neutrons from a pulsed reactor. Test results indicate that the AlGaAs/GaAs photodiodes generate approximately 10 to 20 times less photocurrent during exposure to a pulse of ionizing-radiation than radiation hardened silicon PIN photodiodes. Studies of neutron induced permanent damage in the AlGaAs/GaAs photodiode show only small changes in optical responsivity and a factor of 8 increase in leakage currents after exposure to 3.6 x 10/sup 15/ neutrons/cm/sup 2/ and 900 krad gamma. The silicon PIN photodiode was exposed to only 28% of the fluence used on the AlGaAs photodiodes and we observed a 40% decrease in optical responsivity and a factor of 7000 increase in leakage current.
Statistically optimal perception and learning: from behavior to neural representations
Fiser, József; Berkes, Pietro; Orbán, Gergő; Lengyel, Máté
2010-01-01
Human perception has recently been characterized as statistical inference based on noisy and ambiguous sensory inputs. Moreover, suitable neural representations of uncertainty have been identified that could underlie such probabilistic computations. In this review, we argue that learning an internal model of the sensory environment is another key aspect of the same statistical inference procedure and thus perception and learning need to be treated jointly. We review evidence for statistically optimal learning in humans and animals, and reevaluate possible neural representations of uncertainty based on their potential to support statistically optimal learning. We propose that spontaneous activity can have a functional role in such representations leading to a new, sampling-based, framework of how the cortex represents information and uncertainty. PMID:20153683
Experienced Gray Wolf Optimization Through Reinforcement Learning and Neural Networks.
Emary, E; Zawbaa, Hossam M; Grosan, Crina
2017-01-10
In this paper, a variant of gray wolf optimization (GWO) that uses reinforcement learning principles combined with neural networks to enhance the performance is proposed. The aim is to overcome, by reinforced learning, the common challenge of setting the right parameters for the algorithm. In GWO, a single parameter is used to control the exploration/exploitation rate, which influences the performance of the algorithm. Rather than using a global way to change this parameter for all the agents, we use reinforcement learning to set it on an individual basis. The adaptation of the exploration rate for each agent depends on the agent's own experience and the current terrain of the search space. In order to achieve this, experience repository is built based on the neural network to map a set of agents' states to a set of corresponding actions that specifically influence the exploration rate. The experience repository is updated by all the search agents to reflect experience and to enhance the future actions continuously. The resulted algorithm is called experienced GWO (EGWO) and its performance is assessed on solving feature selection problems and on finding optimal weights for neural networks algorithm. We use a set of performance indicators to evaluate the efficiency of the method. Results over various data sets demonstrate an advance of the EGWO over the original GWO and over other metaheuristics, such as genetic algorithms and particle swarm optimization.
Locally optimal extracellular stimulation for chaotic desynchronization of neural populations.
Wilson, Dan; Moehlis, Jeff
2014-10-01
We use optimal control theory to design a methodology to find locally optimal stimuli for desynchronization of a model of neurons with extracellular stimulation. This methodology yields stimuli which lead to positive Lyapunov exponents, and hence desynchronizes a neural population. We analyze this methodology in the presence of interneuron coupling to make predictions about the strength of stimulation required to overcome synchronizing effects of coupling. This methodology suggests a powerful alternative to pulsatile stimuli for deep brain stimulation as it uses less energy than pulsatile stimuli, and could eliminate the time consuming tuning process.
Dhanarajan, Gunaseelan; Rangarajan, Vivek; Bandi, Chandrakanth; Dixit, Abhivyakti; Das, Susmita; Ale, Kranthikiran; Sen, Ramkrishna
2017-08-20
A lipopeptide biosurfactant produced by marine Bacillus megaterium and a biopolymer produced by thermophilic Bacillus licheniformis were tested for their application potential in the enhanced oil recovery. The crude biosurfactant obtained after acid precipitation effectively reduced the surface tension of deionized water from 70.5 to 28.25mN/m and the interfacial tension between lube oil and water from 18.6 to 1.5mN/m at a concentration of 250mgL(-1). The biosurfactant exhibited a maximum emulsification activity (E24) of 81.66% against lube oil. The lipopeptide micelles were stabilized by addition of Ca(2+) ions to the biosurfactant solution. The oil recovery efficiency of Ca(2+) conditioned lipopeptide solution from a sand-packed column was optimized by using artificial neural network (ANN) modelling coupled with genetic algorithm (GA) optimization. Three important parameters namely lipopeptide concentration, Ca(2+) concentration and solution pH were considered for optimization studies. In order to further improve the recovery efficiency, a water soluble biopolymer produced by Bacillus licheniformis was used as a flooding agent after biosurfactant incubation. Upon ANN-GA optimization, 45% tertiary oil recovery was achieved, when biopolymer at a concentration of 3gL(-1) was used as a flooding agent. Oil recovery was only 29% at optimal conditions predicted by ANN-GA, when only water was used as flooding solution. The important characteristics of biopolymers such as its viscosity, pore plugging capabilities and bio-cementing ability have also been tested. Thus, as a result of biosurfactant incubation and biopolymer flooding under the optimal process conditions, a maximum oil recovery of 45% was achieved. Therefore, this study is novel, timely and interesting for it showed the combined influence of biosurfactant and biopolymer on solubilisation and mobilization of oil from the soil. Copyright © 2017 Elsevier B.V. All rights reserved.
Electronic Nose Based on an Optimized Competition Neural Network
Men, Hong; Liu, Haiyan; Pan, Yunpeng; Wang, Lei; Zhang, Haiping
2011-01-01
In view of the fact that there are disadvantages in that the class number must be determined in advance, the value of learning rates are hard to fix, etc., when using traditional competitive neural networks (CNNs) in electronic noses (E-noses), an optimized CNN method was presented. The optimized CNN was established on the basis of the optimum class number of samples according to the changes of the Davies and Bouldin (DB) value and it could increase, divide, or delete neurons in order to adjust the number of neurons automatically. Moreover, the learning rate changes according to the variety of training times of each sample. The traditional CNN and the optimized CNN were applied to five kinds of sorted vinegars with an E-nose. The results showed that optimized network structures could adjust the number of clusters dynamically and resulted in good classifications. PMID:22163887
A Bi-Projection Neural Network for Solving Constrained Quadratic Optimization Problems.
Xia, Youshen; Wang, Jun
2016-02-01
In this paper, a bi-projection neural network for solving a class of constrained quadratic optimization problems is proposed. It is proved that the proposed neural network is globally stable in the sense of Lyapunov, and the output trajectory of the proposed neural network will converge globally to an optimal solution. Compared with existing projection neural networks (PNNs), the proposed neural network has a very small model size owing to its bi-projection structure. Furthermore, an application to data fusion shows that the proposed neural network is very effective. Numerical results demonstrate that the proposed neural network is much faster than the existing PNNs.
Optimal field-scale groundwater remediation using neural networks and the genetic algorithm
Rogers, L.L.; Dowla, F.U.; Johnson, V.M.
1993-05-01
We present a new approach for field-scale nonlinear management of groundwater remediation. First, an artificial neural network (ANN) is trained to predict the outcome of a groundwater transport simulation. Then a genetic algorithm (GA) searches through possible pumping realizations, evaluating the fitness of each with a prediction from the trained ANN. Traditional approaches rely on optimization algorithms requiring sequential calls of the groundwater transport simulation. Our approach processes the transport simulations in parallel and ``recycles`` the knowledge base of these simulations, greatly reducing the computational and real-time burden, often the primary impediment to developing field-scale management models. We present results from a Superfund site suggesting that such management techniques can reduce cleanup costs by over a hundred million dollars.
Neural mechanism of optimal limb coordination in crustacean swimming.
Zhang, Calvin; Guy, Robert D; Mulloney, Brian; Zhang, Qinghai; Lewis, Timothy J
2014-09-23
A fundamental challenge in neuroscience is to understand how biologically salient motor behaviors emerge from properties of the underlying neural circuits. Crayfish, krill, prawns, lobsters, and other long-tailed crustaceans swim by rhythmically moving limbs called swimmerets. Over the entire biological range of animal size and paddling frequency, movements of adjacent swimmerets maintain an approximate quarter-period phase difference with the more posterior limbs leading the cycle. We use a computational fluid dynamics model to show that this frequency-invariant stroke pattern is the most effective and mechanically efficient paddling rhythm across the full range of biologically relevant Reynolds numbers in crustacean swimming. We then show that the organization of the neural circuit underlying swimmeret coordination provides a robust mechanism for generating this stroke pattern. Specifically, the wave-like limb coordination emerges robustly from a combination of the half-center structure of the local central pattern generating circuits (CPGs) that drive the movements of each limb, the asymmetric network topology of the connections between local CPGs, and the phase response properties of the local CPGs, which we measure experimentally. Thus, the crustacean swimmeret system serves as a concrete example in which the architecture of a neural circuit leads to optimal behavior in a robust manner. Furthermore, we consider all possible connection topologies between local CPGs and show that the natural connectivity pattern generates the biomechanically optimal stroke pattern most robustly. Given the high metabolic cost of crustacean swimming, our results suggest that natural selection has pushed the swimmeret neural circuit toward a connection topology that produces optimal behavior.
Neural mechanism of optimal limb coordination in crustacean swimming
Zhang, Calvin; Guy, Robert D.; Mulloney, Brian; Zhang, Qinghai; Lewis, Timothy J.
2014-01-01
A fundamental challenge in neuroscience is to understand how biologically salient motor behaviors emerge from properties of the underlying neural circuits. Crayfish, krill, prawns, lobsters, and other long-tailed crustaceans swim by rhythmically moving limbs called swimmerets. Over the entire biological range of animal size and paddling frequency, movements of adjacent swimmerets maintain an approximate quarter-period phase difference with the more posterior limbs leading the cycle. We use a computational fluid dynamics model to show that this frequency-invariant stroke pattern is the most effective and mechanically efficient paddling rhythm across the full range of biologically relevant Reynolds numbers in crustacean swimming. We then show that the organization of the neural circuit underlying swimmeret coordination provides a robust mechanism for generating this stroke pattern. Specifically, the wave-like limb coordination emerges robustly from a combination of the half-center structure of the local central pattern generating circuits (CPGs) that drive the movements of each limb, the asymmetric network topology of the connections between local CPGs, and the phase response properties of the local CPGs, which we measure experimentally. Thus, the crustacean swimmeret system serves as a concrete example in which the architecture of a neural circuit leads to optimal behavior in a robust manner. Furthermore, we consider all possible connection topologies between local CPGs and show that the natural connectivity pattern generates the biomechanically optimal stroke pattern most robustly. Given the high metabolic cost of crustacean swimming, our results suggest that natural selection has pushed the swimmeret neural circuit toward a connection topology that produces optimal behavior. PMID:25201976
Evolving Neural Networks for Nonlinear Control.
1996-09-30
An approach to creating Amorphous Recurrent Neural Networks (ARNN) using Genetic Algorithms (GA) called 2pGA has been developed and shown to be...effective in evolving neural networks for the control and stabilization of both linear and nonlinear plants, the optimal control for a nonlinear regulator
Evolving neural network optimization of cholesteryl ester separation by reversed-phase HPLC
Jansen, Michael A.; Kiwata, Jacqueline; Arceo, Jennifer; Faull, Kym F.
2010-01-01
Cholesteryl esters have antimicrobial activity and likely contribute to the innate immunity system. Improved separation techniques are needed to characterize these compounds. In this study, optimization of the reversed-phase high-performance liquid chromatography separation of six analyte standards (four cholesteryl esters plus cholesterol and tri-palmitin) was accomplished by modeling with an artificial neural network–genetic algorithm (ANN-GA) approach. A fractional factorial design was employed to examine the significance of four experimental factors: organic component in the mobile phase (ethanol and methanol), column temperature, and flow rate. Three separation parameters were then merged into geometric means using Derringer’s desirability function and used as input sources for model training and testing. The use of genetic operators proved valuable for the determination of an effective neural network structure. Implementation of the optimized method resulted in complete separation of all six analytes, including the resolution of two previously co-eluting peaks. Model validation was performed with experimental responses in good agreement with model-predicted responses. Improved separation was also realized in a complex biological fluid, human milk. Thus, the first known use of ANN-GA modeling for improving the chromatographic separation of cholesteryl esters in biological fluids is presented and will likely prove valuable for future investigators involved in studying complex biological samples. Figure ANN-derived response surface plot for two interacting factors and overall response Electronic supplementary material The online version of this article (doi:10.1007/s00216-010-3778-5) contains supplementary material, which is available to authorized users. PMID:20490467
The neural optimal control hierarchy for motor control
NASA Astrophysics Data System (ADS)
DeWolf, T.; Eliasmith, C.
2011-10-01
Our empirical, neuroscientific understanding of biological motor systems has been rapidly growing in recent years. However, this understanding has not been systematically mapped to a quantitative characterization of motor control based in control theory. Here, we attempt to bridge this gap by describing the neural optimal control hierarchy (NOCH), which can serve as a foundation for biologically plausible models of neural motor control. The NOCH has been constructed by taking recent control theoretic models of motor control, analyzing the required processes, generating neurally plausible equivalent calculations and mapping them on to the neural structures that have been empirically identified to form the anatomical basis of motor control. We demonstrate the utility of the NOCH by constructing a simple model based on the identified principles and testing it in two ways. First, we perturb specific anatomical elements of the model and compare the resulting motor behavior with clinical data in which the corresponding area of the brain has been damaged. We show that damaging the assigned functions of the basal ganglia and cerebellum can cause the movement deficiencies seen in patients with Huntington's disease and cerebellar lesions. Second, we demonstrate that single spiking neuron data from our model's motor cortical areas explain major features of single-cell responses recorded from the same primate areas. We suggest that together these results show how NOCH-based models can be used to unify a broad range of data relevant to biological motor control in a quantitative, control theoretic framework.
Iterative free-energy optimization for recurrent neural networks (INFERNO)
2017-01-01
The intra-parietal lobe coupled with the Basal Ganglia forms a working memory that demonstrates strong planning capabilities for generating robust yet flexible neuronal sequences. Neurocomputational models however, often fails to control long range neural synchrony in recurrent spiking networks due to spontaneous activity. As a novel framework based on the free-energy principle, we propose to see the problem of spikes’ synchrony as an optimization problem of the neurons sub-threshold activity for the generation of long neuronal chains. Using a stochastic gradient descent, a reinforcement signal (presumably dopaminergic) evaluates the quality of one input vector to move the recurrent neural network to a desired activity; depending on the error made, this input vector is strengthened to hill-climb the gradient or elicited to search for another solution. This vector can be learned then by one associative memory as a model of the basal-ganglia to control the recurrent neural network. Experiments on habit learning and on sequence retrieving demonstrate the capabilities of the dual system to generate very long and precise spatio-temporal sequences, above two hundred iterations. Its features are applied then to the sequential planning of arm movements. In line with neurobiological theories, we discuss its relevance for modeling the cortico-basal working memory to initiate flexible goal-directed neuronal chains of causation and its relation to novel architectures such as Deep Networks, Neural Turing Machines and the Free-Energy Principle. PMID:28282439
Iterative free-energy optimization for recurrent neural networks (INFERNO).
Pitti, Alexandre; Gaussier, Philippe; Quoy, Mathias
2017-01-01
The intra-parietal lobe coupled with the Basal Ganglia forms a working memory that demonstrates strong planning capabilities for generating robust yet flexible neuronal sequences. Neurocomputational models however, often fails to control long range neural synchrony in recurrent spiking networks due to spontaneous activity. As a novel framework based on the free-energy principle, we propose to see the problem of spikes' synchrony as an optimization problem of the neurons sub-threshold activity for the generation of long neuronal chains. Using a stochastic gradient descent, a reinforcement signal (presumably dopaminergic) evaluates the quality of one input vector to move the recurrent neural network to a desired activity; depending on the error made, this input vector is strengthened to hill-climb the gradient or elicited to search for another solution. This vector can be learned then by one associative memory as a model of the basal-ganglia to control the recurrent neural network. Experiments on habit learning and on sequence retrieving demonstrate the capabilities of the dual system to generate very long and precise spatio-temporal sequences, above two hundred iterations. Its features are applied then to the sequential planning of arm movements. In line with neurobiological theories, we discuss its relevance for modeling the cortico-basal working memory to initiate flexible goal-directed neuronal chains of causation and its relation to novel architectures such as Deep Networks, Neural Turing Machines and the Free-Energy Principle.
A One-Layer Recurrent Neural Network for Constrained Complex-Variable Convex Optimization.
Qin, Sitian; Feng, Jiqiang; Song, Jiahui; Wen, Xingnan; Xu, Chen
2016-12-22
In this paper, based on CR calculus and penalty method, a one-layer recurrent neural network is proposed for solving constrained complex-variable convex optimization. It is proved that for any initial point from a given domain, the state of the proposed neural network reaches the feasible region in finite time and converges to an optimal solution of the constrained complex-variable convex optimization finally. In contrast to existing neural networks for complex-variable convex optimization, the proposed neural network has a lower model complexity and better convergence. Some numerical examples and application are presented to substantiate the effectiveness of the proposed neural network.
NASA Astrophysics Data System (ADS)
Frisk, C.; Platzer-Björkman, C.; Olsson, J.; Szaniawski, P.; Wätjen, J. T.; Fjällström, V.; Salomé, P.; Edoff, M.
2014-12-01
Highly efficient Cu(In,Ga)(S,Se)2 photovoltaic thin film solar cells often have a compositional variation of Ga to In in the absorber layer, here described as a Ga-profile. In this work, we have studied the role of Ga-profiles in four different models based on input data from electrical and optical characterizations of an in-house state-of-the-art Cu(In,Ga)Se2 (CIGS) solar cell with power conversion efficiency above 19%. A simple defect model with mid-gap defects in the absorber layer was compared with models with Ga-dependent defect concentrations and amphoteric defects. In these models, optimized single-graded Ga-profiles have been compared with optimized double-graded Ga-profiles. It was found that the defect concentration for effective Shockley-Read-Hall recombination is low for high efficiency CIGS devices and that the doping concentration of the absorber layer, chosen according to the defect model, is paramount when optimizing Ga-profiles. For optimized single-graded Ga-profiles, the simulated power conversion efficiency (depending on the model) is 20.5-20.8%, and the equivalent double-graded Ga-profiles yield 20.6-21.4%, indicating that the bandgap engineering of the CIGS device structure can lead to improvements in efficiency. Apart from the effects of increased doping in the complex defect models, the results are similar when comparing the complex defect models to the simple defect models.
Gueguim-Kana, E B; Oloke, J K; Lateef, A; Zebaze-Kana, M G
2007-07-01
The acidification behavior of Lactobacillus bulgaricus and Streptococcus thermophilus for yoghurt production was investigated along temperature profiles within the optimal window of 38-44 degrees C. For the optimal acidification temperature profile search, an optimization engine module built on a modular artificial neural network (ANN) and genetic algorithm (GA) was used. Fourteen batches of yoghurt fermentations were evaluated using different temperature profiles in order to train and validate the ANN sub-module. The ANN captured the nonlinear relationship between temperature profiles and acidification patterns on training data after 150 epochs. This served as an evaluation function for the GA. The acidification slope of the temperature profile was the performance index. The GA sub-module iteratively evolved better temperature profiles across generations using GA operations. The stopping criterion was met after 11 generations. The optimal profile showed an acidification slope of 0.06117 compared to an initial value of 0.0127 and at a set point sequence of 43, 38, 44, 43, and 39 degrees C. Laboratory evaluation of three replicates of the GA suggested optimum profile of 43, 38, 44, 43, and 39 degrees C gave an average slope of 0.04132. The optimization engine used (to be published elsewhere) could effectively search for optimal profiles of different physico-chemical parameters of fermentation processes.
Behavior and neural basis of near-optimal visual search
Ma, Wei Ji; Navalpakkam, Vidhya; Beck, Jeffrey M; van den Berg, Ronald; Pouget, Alexandre
2013-01-01
The ability to search efficiently for a target in a cluttered environment is one of the most remarkable functions of the nervous system. This task is difficult under natural circumstances, as the reliability of sensory information can vary greatly across space and time and is typically a priori unknown to the observer. In contrast, visual-search experiments commonly use stimuli of equal and known reliability. In a target detection task, we randomly assigned high or low reliability to each item on a trial-by-trial basis. An optimal observer would weight the observations by their trial-to-trial reliability and combine them using a specific nonlinear integration rule. We found that humans were near-optimal, regardless of whether distractors were homogeneous or heterogeneous and whether reliability was manipulated through contrast or shape. We present a neural-network implementation of near-optimal visual search based on probabilistic population coding. The network matched human performance. PMID:21552276
Johnson, V.M.; Rogers, L.L.
1994-09-01
A goal common to both the environmental and petroleum industries is the reduction of costs and/or enhancement of profits by the optimal placement of extraction/production and injection wells. Formal optimization techniques facilitate this goal by searching among the potentially infinite number of possible well patterns for ones that best meet engineering and economic objectives. However, if a flow and transport model or reservoir simulator is being used to evaluate the effectiveness of each network of wells, the computational resources required to apply most optimization techniques to real field problems become prohibitively expensive. This paper describes a new approach to field-scale, nonlinear optimization of well patterns that is intended to make such searches tractable on conventional computer equipment. Artificial neural networks (ANNs) are trained to predict selected information that would normally be calculated by the simulator. The ANNs are then embedded in a variant of the genetic algorithm (GA), which drives the search for increasingly effective well patterns and uses the ANNs, rather than the original simulator, to evaluate the effectiveness of each pattern. Once the search is complete, the ANNs are reused in sensitivity studies to give additional information on the performance of individual or clusters of wells.
Zhang, Gexiang; Rong, Haina; Neri, Ferrante; Pérez-Jiménez, Mario J
2014-08-01
Membrane systems (also called P systems) refer to the computing models abstracted from the structure and the functioning of the living cell as well as from the cooperation of cells in tissues, organs, and other populations of cells. Spiking neural P systems (SNPS) are a class of distributed and parallel computing models that incorporate the idea of spiking neurons into P systems. To attain the solution of optimization problems, P systems are used to properly organize evolutionary operators of heuristic approaches, which are named as membrane-inspired evolutionary algorithms (MIEAs). This paper proposes a novel way to design a P system for directly obtaining the approximate solutions of combinatorial optimization problems without the aid of evolutionary operators like in the case of MIEAs. To this aim, an extended spiking neural P system (ESNPS) has been proposed by introducing the probabilistic selection of evolution rules and multi-neurons output and a family of ESNPS, called optimization spiking neural P system (OSNPS), are further designed through introducing a guider to adaptively adjust rule probabilities to approximately solve combinatorial optimization problems. Extensive experiments on knapsack problems have been reported to experimentally prove the viability and effectiveness of the proposed neural system.
Optimal neural population coding of an auditory spatial cue.
Harper, Nicol S; McAlpine, David
2004-08-05
A sound, depending on the position of its source, can take more time to reach one ear than the other. This interaural (between the ears) time difference (ITD) provides a major cue for determining the source location. Many auditory neurons are sensitive to ITDs, but the means by which such neurons represent ITD is a contentious issue. Recent studies question whether the classical general model (the Jeffress model) applies across species. Here we show that ITD coding strategies of different species can be explained by a unifying principle: that the ITDs an animal naturally encounters should be coded with maximal accuracy. Using statistical techniques and a stochastic neural model, we demonstrate that the optimal coding strategy for ITD depends critically on head size and sound frequency. For small head sizes and/or low-frequency sounds, the optimal coding strategy tends towards two distinct sub-populations tuned to ITDs outside the range created by the head. This is consistent with recent observations in small mammals. For large head sizes and/or high frequencies, the optimal strategy is a homogeneous distribution of ITD tunings within the range created by the head. This is consistent with observations in the barn owl. For humans, the optimal strategy to code ITDs from an acoustically measured distribution depends on frequency; above 400 Hz a homogeneous distribution is optimal, and below 400 Hz distinct sub-populations are optimal.
Solving nonlinear equality constrained multiobjective optimization problems using neural networks.
Mestari, Mohammed; Benzirar, Mohammed; Saber, Nadia; Khouil, Meryem
2015-10-01
This paper develops a neural network architecture and a new processing method for solving in real time, the nonlinear equality constrained multiobjective optimization problem (NECMOP), where several nonlinear objective functions must be optimized in a conflicting situation. In this processing method, the NECMOP is converted to an equivalent scalar optimization problem (SOP). The SOP is then decomposed into several-separable subproblems processable in parallel and in a reasonable time by multiplexing switched capacitor circuits. The approach which we propose makes use of a decomposition-coordination principle that allows nonlinearity to be treated at a local level and where coordination is achieved through the use of Lagrange multipliers. The modularity and the regularity of the neural networks architecture herein proposed make it suitable for very large scale integration implementation. An application to the resolution of a physical problem is given to show that the approach used here possesses some advantages of the point of algorithmic view, and provides processes of resolution often simpler than the usual techniques.
Optimal Control Problem of Feeding Adaptations of Daphnia and Neural Network Simulation
NASA Astrophysics Data System (ADS)
Kmet', Tibor; Kmet'ov, Mria
2010-09-01
A neural network based optimal control synthesis is presented for solving optimal control problems with control and state constraints and open final time. The optimal control problem is transcribed into nonlinear programming problem, which is implemented with adaptive critic neural network [9] and recurrent neural network for solving nonlinear proprojection equations [10]. The proposed simulation methods is illustrated by the optimal control problem of feeding adaptation of filter feeders of Daphnia. Results show that adaptive critic based systematic approach and neural network solving of nonlinear equations hold promise for obtaining the optimal control with control and state constraints and open final time.
Application of fuzzy GA for optimal vibration control of smart cylindrical shells
NASA Astrophysics Data System (ADS)
Jin, Zhanli; Yang, Yaowen; Kiong Soh, Chee
2005-12-01
In this paper, a fuzzy-controlled genetic-based optimization technique for optimal vibration control of cylindrical shell structures incorporating piezoelectric sensor/actuators (S/As) is proposed. The geometric design variables of the piezoelectric patches, including the placement and sizing of the piezoelectric S/As, are processed using fuzzy set theory. The criterion based on the maximization of energy dissipation is adopted for the geometric optimization. A fuzzy-rule-based system (FRBS) representing expert knowledge and experience is incorporated in a modified genetic algorithm (GA) to control its search process. A fuzzy logic integrated GA is then developed and implemented. The results of three numerical examples, which include a simply supported plate, a simply supported cylindrical shell, and a clamped simply supported plate, provide some meaningful and heuristic conclusions for practical design. The results also show that the proposed fuzzy-controlled GA approach is more effective and efficient than the pure GA method.
Implementing size-optimal discrete neural networks require analog circuitry
Beiu, V.
1998-12-01
This paper starts by overviewing results dealing with the approximation capabilities of neural networks, as well as bounds on the size of threshold gate circuits. Based on a constructive solution for Kolmogorov`s superpositions the authors show that implementing Boolean functions can be done using neurons having an identity transfer function. Because in this case the size of the network is minimized, it follows that size-optimal solutions for implementing Boolean functions can be obtained using analog circuitry. Conclusions and several comments on the required precision are ending the paper.
Motion model identification of rescue robot based on optimized Jordan neural network
NASA Astrophysics Data System (ADS)
Zhang, Guangbin; Zhang, Runmei; Wang, Guangyin; Wu, Yulu
2017-06-01
Considering the influence of various factors, such as speed, angle, depth of water, weight, and water flow, on the underwater rescue robot, a method based on neural network is proposed. According to the characteristics of Elman and Jordan neural network, a new dynamic neural network is constructed. The network can be used to remember the state of the hidden layer and increase the feedback of the output node. The improved Jordan network is optimized by chaos particle swarm optimization algorithm. The optimized neural network is applied to identify the dynamic model of the underwater rescue robot. The simulation results show that the neural network has good convergence speed and accuracy.
Zhang, Songchuan; Xia, Youshen; Wang, Jun
2015-12-01
In this paper, we present a complex-valued projection neural network for solving constrained convex optimization problems of real functions with complex variables, as an extension of real-valued projection neural networks. Theoretically, by developing results on complex-valued optimization techniques, we prove that the complex-valued projection neural network is globally stable and convergent to the optimal solution. Obtained results are completely established in the complex domain and thus significantly generalize existing results of the real-valued projection neural networks. Numerical simulations are presented to confirm the obtained results and effectiveness of the proposed complex-valued projection neural network.
Performance optimization of lateral AlGaN/GaN HEMTs with cap gate on 150-mm silicon substrate
NASA Astrophysics Data System (ADS)
Sun, Hui; Liu, Meihua; Liu, Peng; Lin, Xinnan; Cui, Xiaole; Chen, Jianguo; Chen, Dongmin
2017-04-01
A further leakage reduction of AlGaN/GaN HEMTs with cap gate (CG-HEMTs) has been achieved by optimizing the gate structure and the gate etching process. The optimized CG-HEMTs single finger power HEMTs deliver IDSmax = 533 mA/mm at least with gate length of 0.5um and show a median gate leakage current of 20 nA/mm 25 °C measured at a drain voltage of 200 V. The breakdown voltage (BV) of CG-HEMTs was evaluated by the variation of drain-to-gate spacing (LDG) larger than 8 μm. Furthermore, we show that the forward voltage of CG-HEMTs can be improved by shrinking the lateral dimension of the edge termination due to reduced series resistance.
Chai, Rifai; Ling, Sai Ho; Hunter, Gregory P; Tran, Yvonne; Nguyen, Hung T
2014-09-01
This paper presents the classification of a three-class mental task-based brain-computer interface (BCI) that uses the Hilbert-Huang transform for the features extractor and fuzzy particle swarm optimization with cross-mutated-based artificial neural network (FPSOCM-ANN) for the classifier. The experiments were conducted on five able-bodied subjects and five patients with tetraplegia using electroencephalography signals from six channels, and different time-windows of data were examined to find the highest accuracy. For practical purposes, the best two channel combinations were chosen and presented. The three relevant mental tasks used for the BCI were letter composing, arithmetic, and Rubik's cube rolling forward, and these are associated with three wheelchair commands: left, right, and forward, respectively. An additional eyes closed task was collected for testing and used for on-off commands. The results show a dominant alpha wave during eyes closure with average classification accuracy above 90%. The accuracies for patients with tetraplegia were lower compared to the able-bodied subjects; however, this was improved by increasing the duration of the time-windows. The FPSOCM-ANN provides improved accuracies compared to genetic algorithm-based artificial neural network (GA-ANN) for three mental tasks-based BCI classifications with the best classification accuracy achieved for a 7-s time-window: 84.4% (FPSOCM-ANN) compared to 77.4% (GA-ANN). More comparisons on feature extractors and classifiers were included. For two-channel classification, the best two channels were O1 and C4, followed by second best at P3 and O2, and third best at C3 and O2. Mental arithmetic was the most correctly classified task, followed by mental Rubik's cube rolling forward and mental letter composing.
Improving neural networks prediction accuracy using particle swarm optimization combiner.
Elragal, Hassan M
2009-10-01
This paper proposes a technique to improve Artificial Neural Network (ANN) prediction accuracy using Particle Swarm Optimization (PSO) combiner. A hybrid system consists of two stages with the first stage containing two ANNs. The first ANN predictor is a multi-layer feed-forward network trained with error back-propagation and the second predictor is a functional link network. These two predictors are combined in the second stage using PSO combiner in a linear and non-linear fashion. The proposed method is applied to problem of predicting daily natural gas consumption. The performance of ANN predictors and combination methods are tested on real data from four different gas utilities. The experimental results show that the proposed particle swarm optimization combiners results in more accurate prediction compared to using single ANN predictor. Prediction accuracy improvement of the proposed PSO combiners have been shown using hypothesis testing.
Neural dynamic optimization for autonomous aerial vehicle trajectory design
NASA Astrophysics Data System (ADS)
Xu, Peng; Verma, Ajay; Mayer, Richard J.
2007-04-01
Online aerial vehicle trajectory design and reshaping are crucial for a class of autonomous aerial vehicles such as reusable launch vehicles in order to achieve flexibility in real-time flying operations. An aerial vehicle is modeled as a nonlinear multi-input-multi-output (MIMO) system. The inputs include the control parameters and current system states that include velocity and position coordinates of the vehicle. The outputs are the new system states. An ideal trajectory control design system generates a series of control commands to achieve a desired trajectory under various disturbances and vehicle model uncertainties including aerodynamic perturbations caused by geometric damage to the vehicle. Conventional approaches suffer from the nonlinearity of the MIMO system, and the high-dimensionality of the system state space. In this paper, we apply a Neural Dynamic Optimization (NDO) based approach to overcome these difficulties. The core of an NDO model is a multilayer perceptron (MLP) neural network, which generates the control parameters online. The inputs of the MLP are the time-variant states of the MIMO systems. The outputs of the MLP and the control parameters will be used by the MIMO to generate new system states. By such a formulation, an NDO model approximates the time-varying optimal feedback solution.
Structure Learning for Deep Neural Networks Based on Multiobjective Optimization.
Liu, Jia; Gong, Maoguo; Miao, Qiguang; Wang, Xiaogang; Li, Hao
2017-05-05
This paper focuses on the connecting structure of deep neural networks and proposes a layerwise structure learning method based on multiobjective optimization. A model with better generalization can be obtained by reducing the connecting parameters in deep networks. The aim is to find the optimal structure with high representation ability and better generalization for each layer. Then, the visible data are modeled with respect to structure based on the products of experts. In order to mitigate the difficulty of estimating the denominator in PoE, the denominator is simplified and taken as another objective, i.e., the connecting sparsity. Moreover, for the consideration of the contradictory nature between the representation ability and the network connecting sparsity, the multiobjective model is established. An improved multiobjective evolutionary algorithm is used to solve this model. Two tricks are designed to decrease the computational cost according to the properties of input data. The experiments on single-layer level, hierarchical level, and application level demonstrate the effectiveness of the proposed algorithm, and the learned structures can improve the performance of deep neural networks.
2008-01-01
Constrained optimization problems arise in a wide variety of scientific and engineering applications. Since several single recurrent neural networks when applied to solve constrained optimization problems for real-time engineering applications have shown some limitations, cooperative recurrent neural network approaches have been developed to overcome drawbacks of these single recurrent neural networks. This paper surveys in details work on cooperative recurrent neural networks for solving constrained optimization problems and their engineering applications, and points out their standing models from viewpoint of both convergence to the optimal solution and model complexity. We provide examples and comparisons to shown advantages of these models in the given applications. PMID:19003467
Feed Forward Neural Network and Optimal Control Problem with Control and State Constraints
Kmet', Tibor; Kmet'ova, Maria
2009-09-09
A feed forward neural network based optimal control synthesis is presented for solving optimal control problems with control and state constraints. The paper extends adaptive critic neural network architecture proposed by [5] to the optimal control problems with control and state constraints. The optimal control problem is transcribed into a nonlinear programming problem which is implemented with adaptive critic neural network. The proposed simulation method is illustrated by the optimal control problem of nitrogen transformation cycle model. Results show that adaptive critic based systematic approach holds promise for obtaining the optimal control with control and state constraints.
Feed Forward Neural Network and Optimal Control Problem with Control and State Constraints
NASA Astrophysics Data System (ADS)
Kmet', Tibor; Kmet'ová, Mária
2009-09-01
A feed forward neural network based optimal control synthesis is presented for solving optimal control problems with control and state constraints. The paper extends adaptive critic neural network architecture proposed by [5] to the optimal control problems with control and state constraints. The optimal control problem is transcribed into a nonlinear programming problem which is implemented with adaptive critic neural network. The proposed simulation method is illustrated by the optimal control problem of nitrogen transformation cycle model. Results show that adaptive critic based systematic approach holds promise for obtaining the optimal control with control and state constraints.
Optimizing back surface field for improving V oc of (Al)GaInP solar cell
NASA Astrophysics Data System (ADS)
Hongbo, Lu; Xinyi, Li; Wei, Zhang; Dayong, Zhou; Lijie, Sun; Kaijian, Chen
2016-10-01
GaInP and AlGaInP solar cells were grown by metal organic chemical vapor deposition (MOCVD), and theoretical analysis demonstrated that hetero-interface recombination velocity plays an important role in the optimizing of cell performance, especially the interface between base layer and back surface field (BSF). Measurements including lattice-matched growth and pseudo-BSF were taken to optimize BSF design. Significant improvement of V oc in GaInP and AlGaInP solar cells imply that the measures we took are effective and promising for performance improvement in the next generation high efficiency solar cells. Project supported by the National Natural Science Foundation of China (No. 61474076).
2013-09-01
Optimization of the Nonradiative Lifetime of Molecular- Beam-Epitaxy (MBE)-Grown Undoped GaAs/AlGaAs Double Heterostructures (DH) by P...it to the originator. Army Research Laboratory Adelphi, MD 20783-1197 ARL-TR-6660 September 2013 Optimization of the Nonradiative ...REPORT TYPE Final 3. DATES COVERED (From - To) FY2013 4. TITLE AND SUBTITLE Optimization of the Nonradiative Lifetime of Molecular-Beam-Epitaxy
Li, Yongqiang; Abbaspour, Mohammadreza R; Grootendorst, Paul V; Rauth, Andrew M; Wu, Xiao Yu
2015-08-01
This study was performed to optimize the formulation of polymer-lipid hybrid nanoparticles (PLN) for the delivery of an ionic water-soluble drug, verapamil hydrochloride (VRP) and to investigate the roles of formulation factors. Modeling and optimization were conducted based on a spherical central composite design. Three formulation factors, i.e., weight ratio of drug to lipid (X1), and concentrations of Tween 80 (X2) and Pluronic F68 (X3), were chosen as independent variables. Drug loading efficiency (Y1) and mean particle size (Y2) of PLN were selected as dependent variables. The predictive performance of artificial neural networks (ANN) and the response surface methodology (RSM) were compared. As ANN was found to exhibit better recognition and generalization capability over RSM, multi-objective optimization of PLN was then conducted based upon the validated ANN models and continuous genetic algorithms (GA). The optimal PLN possess a high drug loading efficiency (92.4%, w/w) and a small mean particle size (∼100nm). The predicted response variables matched well with the observed results. The three formulation factors exhibited different effects on the properties of PLN. ANN in coordination with continuous GA represent an effective and efficient approach to optimize the PLN formulation of VRP with desired properties.
An Optimal Density Functional Theory Method for GaN and ZnO
Yu, H.G.
2011-08-25
We report an optimal DFT method (bBLYP) for studying the GaN and ZnO systems. It is developed by modifying the exchange functional in the hybrid BLYP method in order to overcome the flaw of traditional DFT that often predict a rather small band gap for those semiconductors. Results show that the bBLYP method can describe not only correct band gaps of both GaN and ZnO wurtzite crystals, but also accurate properties of relevant small molecules. The application study of crystal-cut nanoparticles and nanowires reveals a new mechanism for band gap narrowing in GaN/ZnO.
Tool Steel Heat Treatment Optimization Using Neural Network Modeling
NASA Astrophysics Data System (ADS)
Podgornik, Bojan; Belič, Igor; Leskovšek, Vojteh; Godec, Matjaz
2016-11-01
Optimization of tool steel properties and corresponding heat treatment is mainly based on trial and error approach, which requires tremendous experimental work and resources. Therefore, there is a huge need for tools allowing prediction of mechanical properties of tool steels as a function of composition and heat treatment process variables. The aim of the present work was to explore the potential and possibilities of artificial neural network-based modeling to select and optimize vacuum heat treatment conditions depending on the hot work tool steel composition and required properties. In the current case training of the feedforward neural network with error backpropagation training scheme and four layers of neurons (8-20-20-2) scheme was based on the experimentally obtained tempering diagrams for ten different hot work tool steel compositions and at least two austenitizing temperatures. Results show that this type of modeling can be successfully used for detailed and multifunctional analysis of different influential parameters as well as to optimize heat treatment process of hot work tool steels depending on the composition. In terms of composition, V was found as the most beneficial alloying element increasing hardness and fracture toughness of hot work tool steel; Si, Mn, and Cr increase hardness but lead to reduced fracture toughness, while Mo has the opposite effect. Optimum concentration providing high KIc/HRC ratios would include 0.75 pct Si, 0.4 pct Mn, 5.1 pct Cr, 1.5 pct Mo, and 0.5 pct V, with the optimum heat treatment performed at lower austenitizing and intermediate tempering temperatures.
Wei, Peilian; Si, Zhenjun; Lu, Yao; Yu, Qingfei; Huang, Lei; Xu, Zhinan
2017-08-09
Methylobacillus sp. zju323 was adopted to improve the biosynthesis of pyrroloquinoline quinone (PQQ) by systematic optimization of the fermentation medium. The Plackett-Burman design was implemented to screen for the key medium components for the PQQ production. CoCl2 · 6H2O, ρ-amino benzoic acid, and MgSO4 · 7H2O were found capable of enhancing the PQQ production most significantly. A five-level three-factor central composite design was used to investigate the direct and interactive effects of these variables. Both response surface methodology (RSM) and artificial neural network-genetic algorithm (ANN-GA) were used to predict the PQQ production and to optimize the medium composition. The results showed that the medium optimized by ANN-GA was better than that by RSM in maximizing PQQ production and the experimental PQQ concentration in the ANN-GA-optimized medium was improved by 44.3% compared with that in the unoptimized medium. Further study showed that this ANN-GA-optimized medium was also effective in improving PQQ production by fed-batch mode, reaching the highest PQQ accumulation of 232.0 mg/L, which was about 47.6% increase relative to that in the original medium. The present work provided an optimized medium and developed a fed-batch strategy which might be potentially applicable in industrial PQQ production.
Optimized production and quality control of (68)Ga-EDTMP for small clinical trials.
Mirzaei, Alireza; Jalilian, Amir R; Badbarin, Ali; Mazidi, Mohammad; Mirshojaei, Fatemeh; Geramifar, Parham; Beiki, Davood
2015-07-01
Optimized production and quality control of gallium-68 labeled ethylenediamine tetramethylene phosphonate ((68)Ga-EDTMP) as an efficient PET radiotracer for bone scans have been presented. Efforts have been made to present a fast, efficient, cost-effective and facile protocol for (68)Ga-EDTMP productions for clinical trials. (68)Ga-EDTMP was prepared using generator-based (68)GaCl3 and EDTMP at optimized conditions for time, temperature, ligand amount, gallium content followed by proper formulation. The biodistribution of the tracer in rats was studied using tissue counting and PET/CT imaging up to 155 min. (68)Ga-EDTMP was prepared at optimized conditions in 5-10 min at 50-60 °C (radiochemical purity ≈99 ± 0.88 % ITLC, >99 % HPLC, specific activity: 15-18 GBq/mM). The biodistribution of the tracer demonstrated high bone uptake of the tracer in 10-20 min while yielding the best images in 2 h. The whole production and quality control of (68)Ga-EDTMP including labeling, purification, HPLC analysis, sterilization and LAL test took 18-20 min with significant specific activity for administration to limited number of patients in a PET center.
Liu, Qingshan; Dang, Chuangyin; Huang, Tingwen
2013-02-01
This paper presents a decision-making model described by a recurrent neural network for dynamic portfolio optimization. The portfolio-optimization problem is first converted into a constrained fractional programming problem. Since the objective function in the programming problem is not convex, the traditional optimization techniques are no longer applicable for solving this problem. Fortunately, the objective function in the fractional programming is pseudoconvex on the feasible region. It leads to a one-layer recurrent neural network modeled by means of a discontinuous dynamic system. To ensure the optimal solutions for portfolio optimization, the convergence of the proposed neural network is analyzed and proved. In fact, the neural network guarantees to get the optimal solutions for portfolio-investment advice if some mild conditions are satisfied. A numerical example with simulation results substantiates the effectiveness and illustrates the characteristics of the proposed neural network.
Designing Artificial Neural Networks Using Particle Swarm Optimization Algorithms.
Garro, Beatriz A; 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.
Designing Artificial Neural Networks Using Particle Swarm Optimization Algorithms
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
Optimization of a fermentation medium using neural networks and genetic algorithms.
Nagata, Yuko; Chu, Khim Hoong
2003-11-01
Artificial neural networks and genetic algorithms are used to model and optimize a fermentation medium for the production of the enzyme hydantoinase by Agrobacterium radiobacter. Experimental data reported in the literature were used to build two neural network models. The concentrations of four medium components served as inputs to the neural network models, and hydantoinase or cell concentration served as a single output of each model. Genetic algorithms were used to optimize the input space of the neural network models to find the optimum settings for maximum enzyme and cell production. Using this procedure, two artificial intelligence techniques have been effectively integrated to create a powerful tool for process modeling and optimization.
Self-organization in neural networks - Applications in structural optimization
NASA Technical Reports Server (NTRS)
Hajela, Prabhat; Fu, B.; Berke, Laszlo
1993-01-01
The present paper discusses the applicability of ART (Adaptive Resonance Theory) networks, and the Hopfield and Elastic networks, in problems of structural analysis and design. A characteristic of these network architectures is the ability to classify patterns presented as inputs into specific categories. The categories may themselves represent distinct procedural solution strategies. The paper shows how this property can be adapted in the structural analysis and design problem. A second application is the use of Hopfield and Elastic networks in optimization problems. Of particular interest are problems characterized by the presence of discrete and integer design variables. The parallel computing architecture that is typical of neural networks is shown to be effective in such problems. Results of preliminary implementations in structural design problems are also included in the paper.
HYBRID NEURAL NETWORK AND SUPPORT VECTOR MACHINE METHOD FOR OPTIMIZATION
NASA Technical Reports Server (NTRS)
Rai, Man Mohan (Inventor)
2005-01-01
System and method for optimization of a design associated with a response function, using a hybrid neural net and support vector machine (NN/SVM) analysis to minimize or maximize an objective function, optionally subject to one or more constraints. As a first example, the NN/SVM analysis is applied iteratively to design of an aerodynamic component, such as an airfoil shape, where the objective function measures deviation from a target pressure distribution on the perimeter of the aerodynamic component. As a second example, the NN/SVM analysis is applied to data classification of a sequence of data points in a multidimensional space. The NN/SVM analysis is also applied to data regression.
Hybrid Neural Network and Support Vector Machine Method for Optimization
NASA Technical Reports Server (NTRS)
Rai, Man Mohan (Inventor)
2007-01-01
System and method for optimization of a design associated with a response function, using a hybrid neural net and support vector machine (NN/SVM) analysis to minimize or maximize an objective function, optionally subject to one or more constraints. As a first example, the NN/SVM analysis is applied iteratively to design of an aerodynamic component, such as an airfoil shape, where the objective function measures deviation from a target pressure distribution on the perimeter of the aerodynamic component. As a second example, the NN/SVM analysis is applied to data classification of a sequence of data points in a multidimensional space. The NN/SVM analysis is also applied to data regression.
Self-organization in neural networks - Applications in structural optimization
NASA Technical Reports Server (NTRS)
Hajela, Prabhat; Fu, B.; Berke, Laszlo
1993-01-01
The present paper discusses the applicability of ART (Adaptive Resonance Theory) networks, and the Hopfield and Elastic networks, in problems of structural analysis and design. A characteristic of these network architectures is the ability to classify patterns presented as inputs into specific categories. The categories may themselves represent distinct procedural solution strategies. The paper shows how this property can be adapted in the structural analysis and design problem. A second application is the use of Hopfield and Elastic networks in optimization problems. Of particular interest are problems characterized by the presence of discrete and integer design variables. The parallel computing architecture that is typical of neural networks is shown to be effective in such problems. Results of preliminary implementations in structural design problems are also included in the paper.
Optimization of GaN Nanorod Growth Conditions for Coalescence Overgrowth
2016-02-04
AFRL-AFOSR-JP-TR-2016-0031 Optimization of GaN Nanorod Growth Conditions for Coalescence Overgrowth Chih-Chung Yang NATIONAL TAIWAN UNIVERSITY Final...REPORT TYPE Final 3. DATES COVERED (From - To) 29-11-2013 to 28-05-2015 4. TITLE AND SUBTITLE Optimization of GaN Nanorod Growth Conditions for...NUMBER 5e. TASK NUMBER 5f. WORK UNIT NUMBER 7. PERFORMING ORGANIZATION NAME(S) AND ADDRESS(ES) NATIONAL TAIWAN UNIVERSITY 1 ROOSEVELT RD. SEC. 4
1998-05-01
Coverage Probability with a Random Optimization Procedure: An Artificial Neural Network Approach by Biing T. Guan, George Z. Gertner, and Alan B...Modeling Training Site Vegetation Coverage Probability with a Random Optimizing Procedure: An Artificial Neural Network Approach 6. AUTHOR(S) Biing...coverage based on past coverage. Approach A literature survey was conducted to identify artificial neural network analysis techniques applicable for
Neural network based optimal control of HVAC&R systems
NASA Astrophysics Data System (ADS)
Ning, Min
Heating, Ventilation, Air-Conditioning and Refrigeration (HVAC&R) systems have wide applications in providing a desired indoor environment for different types of buildings. It is well acknowledged that 30%-40% of the total energy generated is consumed by buildings and HVAC&R systems alone account for more than 50% of the building energy consumption. Low operational efficiency especially under partial load conditions and poor control are part of reasons for such high energy consumption. To improve energy efficiency, HVAC&R systems should be properly operated to maintain a comfortable and healthy indoor environment under dynamic ambient and indoor conditions with the least energy consumption. This research focuses on the optimal operation of HVAC&R systems. The optimization problem is formulated and solved to find the optimal set points for the chilled water supply temperature, discharge air temperature and AHU (air handling unit) fan static pressure such that the indoor environment is maintained with the least chiller and fan energy consumption. To achieve this objective, a dynamic system model is developed first to simulate the system behavior under different control schemes and operating conditions. The system model is modular in structure, which includes a water-cooled vapor compression chiller model and a two-zone VAV system model. A fuzzy-set based extended transformation approach is then applied to investigate the uncertainties of this model caused by uncertain parameters and the sensitivities of the control inputs with respect to the interested model outputs. A multi-layer feed forward neural network is constructed and trained in unsupervised mode to minimize the cost function which is comprised of overall energy cost and penalty cost when one or more constraints are violated. After training, the network is implemented as a supervisory controller to compute the optimal settings for the system. In order to implement the optimal set points predicted by the
On the physical operation and optimization of the p-GaN gate in normally-off GaN HEMT devices
NASA Astrophysics Data System (ADS)
Efthymiou, L.; Longobardi, G.; Camuso, G.; Chien, T.; Chen, M.; Udrea, F.
2017-03-01
In this study, an investigation is undertaken to determine the effect of gate design parameters on the on-state characteristics (threshold voltage and gate turn-on voltage) of pGaN/AlGaN/GaN high electron mobility transistors (HEMTs). Design parameters considered are pGaN doping and gate metal work function. The analysis considers the effects of variations on these parameters using a TCAD model matched with experimental results. A better understanding of the underlying physics governing the operation of these devices is achieved with a view to enable better optimization of such gate designs.
Xia, Youshen; Feng, Gang; Wang, Jun
2008-08-01
This paper presents a novel recurrent neural network for solving nonlinear optimization problems with inequality constraints. Under the condition that the Hessian matrix of the associated Lagrangian function is positive semidefinite, it is shown that the proposed neural network is stable at a Karush-Kuhn-Tucker point in the sense of Lyapunov and its output trajectory is globally convergent to a minimum solution. Compared with variety of the existing projection neural networks, including their extensions and modification, for solving such nonlinearly constrained optimization problems, it is shown that the proposed neural network can solve constrained convex optimization problems and a class of constrained nonconvex optimization problems and there is no restriction on the initial point. Simulation results show the effectiveness of the proposed neural network in solving nonlinearly constrained optimization problems.
Woodward, Alexander; Froese, Tom; Ikegami, Takashi
2015-02-01
The state space of a conventional Hopfield network typically exhibits many different attractors of which only a small subset satisfies constraints between neurons in a globally optimal fashion. It has recently been demonstrated that combining Hebbian learning with occasional alterations of normal neural states avoids this problem by means of self-organized enlargement of the best basins of attraction. However, so far it is not clear to what extent this process of self-optimization is also operative in real brains. Here we demonstrate that it can be transferred to more biologically plausible neural networks by implementing a self-optimizing spiking neural network model. In addition, by using this spiking neural network to emulate a Hopfield network with Hebbian learning, we attempt to make a connection between rate-based and temporal coding based neural systems. Although further work is required to make this model more realistic, it already suggests that the efficacy of the self-optimizing process is independent from the simplifying assumptions of a conventional Hopfield network. We also discuss natural and cultural processes that could be responsible for occasional alteration of neural firing patterns in actual brains.
Saborido, Rubén; Ruiz, Ana B; Luque, Mariano
2016-02-08
In this article, we propose a new evolutionary algorithm for multiobjective optimization called Global WASF-GA (global weighting achievement scalarizing function genetic algorithm), which falls within the aggregation-based evolutionary algorithms. The main purpose of Global WASF-GA is to approximate the whole Pareto optimal front. Its fitness function is defined by an achievement scalarizing function (ASF) based on the Tchebychev distance, in which two reference points are considered (both utopian and nadir objective vectors) and the weight vector used is taken from a set of weight vectors whose inverses are well-distributed. At each iteration, all individuals are classified into different fronts. Each front is formed by the solutions with the lowest values of the ASF for the different weight vectors in the set, using the utopian vector and the nadir vector as reference points simultaneously. Varying the weight vector in the ASF while considering the utopian and the nadir vectors at the same time enables the algorithm to obtain a final set of nondominated solutions that approximate the whole Pareto optimal front. We compared Global WASF-GA to MOEA/D (different versions) and NSGA-II in two-, three-, and five-objective problems. The computational results obtained permit us to conclude that Global WASF-GA gets better performance, regarding the hypervolume metric and the epsilon indicator, than the other two algorithms in many cases, especially in three- and five-objective problems.
Sub-problem Optimization With Regression and Neural Network Approximators
NASA Technical Reports Server (NTRS)
Guptill, James D.; Hopkins, Dale A.; Patnaik, Surya N.
2003-01-01
Design optimization of large systems can be attempted through a sub-problem strategy. In this strategy, the original problem is divided into a number of smaller problems that are clustered together to obtain a sequence of sub-problems. Solution to the large problem is attempted iteratively through repeated solutions to the modest sub-problems. This strategy is applicable to structures and to multidisciplinary systems. For structures, clustering the substructures generates the sequence of sub-problems. For a multidisciplinary system, individual disciplines, accounting for coupling, can be considered as sub-problems. A sub-problem, if required, can be further broken down to accommodate sub-disciplines. The sub-problem strategy is being implemented into the NASA design optimization test bed, referred to as "CometBoards." Neural network and regression approximators are employed for reanalysis and sensitivity analysis calculations at the sub-problem level. The strategy has been implemented in sequential as well as parallel computational environments. This strategy, which attempts to alleviate algorithmic and reanalysis deficiencies, has the potential to become a powerful design tool. However, several issues have to be addressed before its full potential can be harnessed. This paper illustrates the strategy and addresses some issues.
Hybrid binary GA-EDA algorithms for complex “black-box” optimization problems
NASA Astrophysics Data System (ADS)
Sopov, E.
2017-02-01
Genetic Algorithms (GAs) have proved their efficiency solving many complex optimization problems. GAs can be also applied for “black-box” problems, because they realize the “blind” search and do not require any specific information about features of search space and objectives. It is clear that a GA uses the “Trial-and-Error” strategy to explorer search space, and collects some statistical information that is stored in the form of genes in the population. Estimation of Distribution Algorithms (EDA) have very similar realization as GAs, but use an explicit representation of search experience in the form of the statistical probabilities distribution. In this study we discus some approaches for improving the standard GA performance by combining the binary GA with EDA. Finally, a novel approach for the large-scale global optimization is proposed. The experimental results and comparison with some well-studied techniques are presented and discussed.
Optimization of InGaP metamorphic buffers grown by MOVPE
NASA Astrophysics Data System (ADS)
Ebert, C.; Pulwin, Z.; Reynolds, C. L.; Ramos Sn., F.; Li, Y.; Farrell, S.
2015-03-01
Inverted metamorphic multijunction solar cells have shown high solar conversion efficiencies and utilized InGaP based metamorphic (MM) buffers to change the lattice constant using compositional graded buffer layers while minimizing dislocation density in the final material layers. In this study, optimization of InGaP metamorphic buffers was done by systematically exploring key metalorganic vapor phase epitaxy (MOVPE) growth conditions and the MM buffer epitaxial stack structure. To optimize MOVPE growth parameters, growth temperature and V/III ratio were varied during the growth of a standard MM buffer test structure and the final InGaP buffer layer was characterized by photoluminescence, X-ray reciprocal space maps, atomic force microscope, cathodoluminesence, and ex situ bow measurements. The in situ measurement of wafer curvature was also monitored during MM buffer layer growth. Evaluation of material characterization data provided optimized growth conditions for the InGaP based MM buffer. The second part of this study evaluated the actual layer thickness and number of compositional graded steps in a MM buffer. Our results showed that in situ deflectometer measurements of the wafer curvature of the MM buffer layer can be correlated to ex situ determined strain relaxation of the final buffer layer of the MM buffer. Process optimization tests showed a growth temperature of 580 °C with a V/III ratio of 37 provided for the best surface roughness, highest PL intensity and also allowed for low dislocation defect density of the final buffer layer. Using the optimized growth conditions, further optimization of the step grade layers showed that a 350 nm thick grade layer for a six step layer MM buffer for a final buffer composition targeted for In0.8Ga0.2P provided the best surface roughness and 100% final buffer relaxation.
Amaritsakul, Yongyut; Chao, Ching-Kong
2013-01-01
Short-segment instrumentation for spine fractures is threatened by relatively high failure rates. Failure of the spinal pedicle screws including breakage and loosening may jeopardize the fixation integrity and lead to treatment failure. Two important design objectives, bending strength and pullout strength, may conflict with each other and warrant a multiobjective optimization study. In the present study using the three-dimensional finite element (FE) analytical results based on an L25 orthogonal array, bending and pullout objective functions were developed by an artificial neural network (ANN) algorithm, and the trade-off solutions known as Pareto optima were explored by a genetic algorithm (GA). The results showed that the knee solutions of the Pareto fronts with both high bending and pullout strength ranged from 92% to 94% of their maxima, respectively. In mechanical validation, the results of mathematical analyses were closely related to those of experimental tests with a correlation coefficient of −0.91 for bending and 0.93 for pullout (P < 0.01 for both). The optimal design had significantly higher fatigue life (P < 0.01) and comparable pullout strength as compared with commercial screws. Multiobjective optimization study of spinal pedicle screws using the hybrid of ANN and GA could achieve an ideal with high bending and pullout performances simultaneously. PMID:23983810
Amaritsakul, Yongyut; Chao, Ching-Kong; Lin, Jinn
2013-01-01
Short-segment instrumentation for spine fractures is threatened by relatively high failure rates. Failure of the spinal pedicle screws including breakage and loosening may jeopardize the fixation integrity and lead to treatment failure. Two important design objectives, bending strength and pullout strength, may conflict with each other and warrant a multiobjective optimization study. In the present study using the three-dimensional finite element (FE) analytical results based on an L25 orthogonal array, bending and pullout objective functions were developed by an artificial neural network (ANN) algorithm, and the trade-off solutions known as Pareto optima were explored by a genetic algorithm (GA). The results showed that the knee solutions of the Pareto fronts with both high bending and pullout strength ranged from 92% to 94% of their maxima, respectively. In mechanical validation, the results of mathematical analyses were closely related to those of experimental tests with a correlation coefficient of -0.91 for bending and 0.93 for pullout (P < 0.01 for both). The optimal design had significantly higher fatigue life (P < 0.01) and comparable pullout strength as compared with commercial screws. Multiobjective optimization study of spinal pedicle screws using the hybrid of ANN and GA could achieve an ideal with high bending and pullout performances simultaneously.
Optimal exponential synchronization of general chaotic delayed neural networks: an LMI approach.
Liu, Meiqin
2009-09-01
This paper investigates the optimal exponential synchronization problem of general chaotic neural networks with or without time delays by virtue of Lyapunov-Krasovskii stability theory and the linear matrix inequality (LMI) technique. This general model, which is the interconnection of a linear delayed dynamic system and a bounded static nonlinear operator, covers several well-known neural networks, such as Hopfield neural networks, cellular neural networks (CNNs), bidirectional associative memory (BAM) networks, and recurrent multilayer perceptrons (RMLPs) with or without delays. Using the drive-response concept, time-delay feedback controllers are designed to synchronize two identical chaotic neural networks as quickly as possible. The control design equations are shown to be a generalized eigenvalue problem (GEVP) which can be easily solved by various convex optimization algorithms to determine the optimal control law and the optimal exponential synchronization rate. Detailed comparisons with existing results are made and numerical simulations are carried out to demonstrate the effectiveness of the established synchronization laws.
Optimal temperature profiles for annealing of GaAs-crystals
NASA Astrophysics Data System (ADS)
Metzger, Michael; Backofen, Rainer
2000-11-01
The modelling and optimisation of the thermal post-processing for bulk GaAs crystals is described. The annealing takes place in an approximately axisymmetric tube furnace and improves the crystal quality due to a more homogeneous distribution of defects and dopants. For this purpose the crystal has to be heated up to a certain temperature, as fast as possible for economical reasons. The crucial point is to minimise thermally induced stresses during heating. For this optimisation an algorithm based on a reduced order model (ROM) of the heating process is developed. By the aid of this model-predictive control (MPC) algorithm the required time to achieve the annealing temperature was decreased by 30% while the thermoelastic stress in the crystal is reduced by 10% compared to a standard procedure.
Theoretical modeling and optimization of III-V GaInP/GaAs/Ge monolithic triple-junction solar cells
NASA Astrophysics Data System (ADS)
Leem, Jung Woo; Yu, Jae Su; Kim, Jong Nam; Noh, Sam Kyu
2014-05-01
We design and optimize monolithic III-V GaInP/GaAs/Ge triple-junction (TJ) solar cells by using a commercial software Silvaco ATLAS simulator to obtain the maximum short-circuit current density J sc . The maximum J sc , which is a current matching value between the GaInP top and GaAs middle subcells, can be determined by varying the base thicknesses of the GaInP top and GaAs middle subcells. From the numerical simulation results, a matched maximum J sc value of 13.92 mA/cm2 is obtained at base thicknesses of 0.57 μm and 3 μm for the GaInP top and GaAs middle subcells, respectively, under 1-sun air mass 1.5 global spectrum illumination, leading to a high power conversion efficiency of 30.72%. The open-circuit voltage and the fill factor are 2.55 V and 86.55%, respectively. For the optimized cell structure, the external quantum efficiency and the photogeneration rate distributions are also investigated. To obtain efficient antireflection coatings (ARCs), we perform optical reflectance calculations by using a rigorous coupled-wave analysis method. For this, a silicon oxide/titanium oxide double-layer is used as an ARC on the TJ solar cell.
Quantum-based algorithm for optimizing artificial neural networks.
Tzyy-Chyang Lu; Gwo-Ruey Yu; Jyh-Ching Juang
2013-08-01
This paper presents a quantum-based algorithm for evolving artificial neural networks (ANNs). The aim is to design an ANN with few connections and high classification performance by simultaneously optimizing the network structure and the connection weights. Unlike most previous studies, the proposed algorithm uses quantum bit representation to codify the network. As a result, the connectivity bits do not indicate the actual links but the probability of the existence of the connections, thus alleviating mapping problems and reducing the risk of throwing away a potential candidate. In addition, in the proposed model, each weight space is decomposed into subspaces in terms of quantum bits. Thus, the algorithm performs a region by region exploration, and evolves gradually to find promising subspaces for further exploitation. This is helpful to provide a set of appropriate weights when evolving the network structure and to alleviate the noisy fitness evaluation problem. The proposed model is tested on four benchmark problems, namely breast cancer and iris, heart, and diabetes problems. The experimental results show that the proposed algorithm can produce compact ANN structures with good generalization ability compared to other algorithms.
Chaibva, Faith; Burton, Michael; Walker, Roderick B.
2010-01-01
An artificial neural network was used to optimize the release of salbutamol sulfate from hydrophilic matrix formulations. Model formulations to be used for training, testing and validating the neural network were manufactured with the aid of a central composite design with varying the levels of Methocel® K100M, xanthan gum, Carbopol® 974P and Surelease® as the input factors. In vitro dissolution time profiles at six different sampling times were used as target data in training the neural network for formulation optimization. A multi layer perceptron with one hidden layer was constructed using Matlab®, and the number of nodes in the hidden layer was optimized by trial and error to develop a model with the best predictive ability. The results revealed that a neural network with nine nodes was optimal for developing and optimizing formulations. Simulations undertaken with the training data revealed that the constructed model was useable. The optimized neural network was used for optimization of formulation with desirable release characteristics and the results indicated that there was agreement between the predicted formulation and the manufactured formulation. This work illustrates the possible utility of artificial neural networks for the optimization of pharmaceutical formulations with desirable performance characteristics. PMID:27721350
A performance optimization and analysis of graphene based schottky barrier GaAs solar cell
NASA Astrophysics Data System (ADS)
Jolson Singh, Khomdram; Chettri, Dhanu; Jayenta Singh, Thokchom; Thingujam, Terirama; Sarkar, Subir kumar
2017-06-01
Performance optimization of Graphene-GaAs schottky barrier solar cell have been performed by considering variables such as substrate thickness, Graphene thickness, dependence between graphene work function and transmittance. The optimized parameter was extensively used to numerically model the design using TCAD Atlas. The results show the enhanced performance of the design with the optimized thickness of Graphene (0.3μm) and GaAs (10μm), resulting in significant increase in power conversion efficiency from 0.732% to 2.581% and reasonable fill factor up to 70%. It was further analysed that maximum potential was developed in the vicinity of the anode, which results in better charge collection hence improving the overall performance of the solar cell. The results are validated with the reported experimental work.
Qin, Sitian; Yang, Xiudong; Xue, Xiaoping; Song, Jiahui
2016-05-24
Pseudoconvex optimization problem, as an important nonconvex optimization problem, plays an important role in scientific and engineering applications. In this paper, a recurrent one-layer neural network is proposed for solving the pseudoconvex optimization problem with equality and inequality constraints. It is proved that from any initial state, the state of the proposed neural network reaches the feasible region in finite time and stays there thereafter. It is also proved that the state of the proposed neural network is convergent to an optimal solution of the related problem. Compared with the related existing recurrent neural networks for the pseudoconvex optimization problems, the proposed neural network in this paper does not need the penalty parameters and has a better convergence. Meanwhile, the proposed neural network is used to solve three nonsmooth optimization problems, and we make some detailed comparisons with the known related conclusions. In the end, some numerical examples are provided to illustrate the effectiveness of the performance of the proposed neural network.
Arefi-Oskoui, Samira; Khataee, Alireza; Vatanpour, Vahid
2017-07-10
In this research, MgAl-CO3(2-) nanolayered double hydroxide (NLDH) was synthesized through a facile coprecipitation method, followed by a hydrothermal treatment. The prepared NLDHs were used as a hydrophilic nanofiller for improving the performance of the PVDF-based ultrafiltration membranes. The main objective of this research was to obtain the optimized formula of NLDH/PVDF nanocomposite membrane presenting the best performance using computational techniques as a cost-effective method. For this aim, an artificial neural network (ANN) model was developed for modeling and expressing the relationship between the performance of the nanocomposite membrane (pure water flux, protein flux and flux recovery ratio) and the affecting parameters including the NLDH, PVP 29000 and polymer concentrations. The effects of the mentioned parameters and the interaction between the parameters were investigated using the contour plot predicted with the developed model. Scanning electron microscopy (SEM), atomic force microscopy (AFM), and water contact angle techniques were applied to characterize the nanocomposite membranes and to interpret the predictions of the ANN model. The developed ANN model was introduced to genetic algorithm (GA) as a bioinspired optimizer to determine the optimum values of input parameters leading to high pure water flux, protein flux, and flux recovery ratio. The optimum values for NLDH, PVP 29000 and the PVDF concentration were determined to be 0.54, 1, and 18 wt %, respectively. The performance of the nanocomposite membrane prepared using the optimum values proposed by GA was investigated experimentally, in which the results were in good agreement with the values predicted by ANN model with error lower than 6%. This good agreement confirmed that the nanocomposite membranes prformance could be successfully modeled and optimized by ANN-GA system.
NASA Astrophysics Data System (ADS)
Wei, Qiu-lin; Guo, Zuo-xing; Zhao, Lei; Zhao, Liang; Yuan, De-zeng; Miao, Guo-qing; Xia, Mao-sheng
2016-11-01
Microstructure and misfit dislocation behavior in In x Ga1- x As/InP heteroepitaxial materials grown by low pressure metal organic chemical vapor deposition (LP-MOCVD) were analyzed by high resolution transmission electron microscopy (HRTEM), scanning electron microscopy (SEM), atomic force microscopy (AFM), Raman spectroscopy and Hall effect measurements. To optimize the structure of In0.82Ga0.18As/InP heterostructure, the In x Ga1- x As buffer layer was grown. The residual strain of the In0.82Ga0.18As epitaxial layer was calculated. Further, the periodic growth pattern of the misfit dislocation at the interface was discovered and verified. Then the effects of misfit dislocation on the surface morphology and microstructure of the material were studied. It is found that the misfit dislocation of high indium (In) content In0.82Ga0.82As epitaxial layer has significant influence on the carrier concentration.
Optimization of drilling characteristics for Al/SiCp composites using fuzzy/GA
NASA Astrophysics Data System (ADS)
Karthikeyan, R.; Jaiganesh, S.; Pai, B. C.
2002-04-01
In this paper an attempt has been made to optimize the drilling characteristics for Al/SiCp composites using fuzzy logic and genetic algorithms (GA). The drilling characteristics studied were drill wear, specific energy and surface roughness. The parameters considered for the study include volume fraction of SiC in the aluminium matrix, cutting speed and feed rate. The experimental data was trained and simulated using fuzzy logic and optimization of cutting conditions were performed using genetic algorithms. The optimized cutting conditions were validated using confirmation experiments.
Optimal Power Flow Solution Using GA-Fuzzy and PSO-Fuzzy
NASA Astrophysics Data System (ADS)
Kumar, S.; Chaturvedi, D. K.
2014-12-01
The power flow problem deals with certain controllable variables that are adjusted to minimize operating costs, while satisfying operating limits on various controls, dependent variables and function of variables. This paper presents an efficient and reliable nature inspired based approach to solve the optimal power flow (OPF) problems. The proposed approach employs the integration of Fuzzy Systems with genetic algorithm (GA) and particle swarm optimization (PSO) algorithm for optimal setting of OPF problem control variables. The proposed approach has been applied on the modified IEEE 30-bus test system with minimizing the operating costs of system. The results have been compared with the results reported in the literature.
NASA Technical Reports Server (NTRS)
Boussalis, Dhemetrios; Wang, Shyh J.
1992-01-01
This paper presents a method for utilizing artificial neural networks for direct adaptive control of dynamic systems with poorly known dynamics. The neural network weights (controller gains) are adapted in real time using state measurements and a random search optimization algorithm. The results are demonstrated via simulation using two highly nonlinear systems.
NASA Technical Reports Server (NTRS)
Boussalis, Dhemetrios; Wang, Shyh J.
1992-01-01
This paper presents a method for utilizing artificial neural networks for direct adaptive control of dynamic systems with poorly known dynamics. The neural network weights (controller gains) are adapted in real time using state measurements and a random search optimization algorithm. The results are demonstrated via simulation using two highly nonlinear systems.
NASA Astrophysics Data System (ADS)
Cao, Longchao; Yang, Yang; Jiang, Ping; Zhou, Qi; Mi, Gaoyang; Gao, Zhongmei; Rong, Youmin; Wang, Chunming
The external static magnetic field has significant influence on the microstructure and mechanical properties of weld bead during 316L stainless steel laser welding. The quality of a weld joint of laser welding supported by external magnetic field (LWSMF) is significantly influenced by the processing parameters. Hence, how to choose appropriate processing parameters for a good-quality weld joint of LWSMF is significantly important. This paper develops a hybrid methodology by combining radial basis function neural network (RBFNN) and genetic algorithm (GA) to address this issue. Firstly, the bead appearance, which is the external manifestation of the weld geometrical imperfection and weld quality, is quantitatively described and selected as the indices to judge the weld quality of LWSMF. Then the physical experiments are conducted, where laser power (LP), laser welding speed (WS), and the flux density of magnetic field (MFD) are taken into consideration as the input process parameters. Secondly, the RBFNN model, as its excellent global prediction performance, is adopted to establish the relationships between the inputs and outputs. Thirdly, based on the constructed RBFNN model, the effects of different input parameters on the bead appearance are analyzed and the global process parameter space exploration is performed by using GA. At last, the verification experiments are conducted to verify the effectiveness of the calculated optimal process parameters. Results demonstrate that the spatter defects decrease and the grains are refined under the influence of external magnetic after optimization. On the whole, the proposed hybrid methodology shows great promise for improving the effectiveness and stability of LWSMF.
Chemical beam epitaxy growth and optimization of InAs/GaAs quantum dot multilayers
NASA Astrophysics Data System (ADS)
Zribi, Jihene; Ilahi, Bouraoui; Morris, Denis; Aimez, Vincent; Arès, Richard
2013-12-01
This paper reports on an in-situ growth process used to optimize InAs/GaAs quantum dot (QD) multilayer structures grown on (001) GaAs substrate by chemical beam epitaxy (CBE). Defects related to the incoherently relaxed InAs clusters are found to alter the QD nucleation mechanism on the subsequent layers, leading to reduced QD density and photoluminescence intensity. The formation of poor crystalline quality clusters is avoided by growing the GaAs spacer layers in a two-step process. The technique consists in covering the InAs QD layer with a 10 nm-thick GaAs layer grown at 465 °C, and then removing the excess indium contained in the uncapped portion of the clusters by increasing the temperature to 565 °C for 10 min before the deposition of the remaining GaAs spacer layer. Morphological investigation shows that the QD density and size distribution obtained in the first layer are preserved up to the tenth layer. The QD integrated photoluminescence intensity is found to increase linearly with the number of stacked layers. These results are very promising for chemical beam growth of high performance intermediate-band solar cells.
Device and Design Optimization for AlGaN/GaN X-Band-Power-Amplifiers with High Efficiency
NASA Astrophysics Data System (ADS)
Kühn, Jutta; van Raay, Friedbert; Quay, Rüdiger; Kiefer, Rudolf; Mikulla, Michael; Seelmann-Eggebert, Matthias; Bronner, Wolfgang; Schlechtweg, Michael; Ambacher, Oliver; Thumm, Manfred
2010-03-01
The design, realization and characterization of dual-stage X-band high-power and highly-efficient monolithic microwave integrated circuit (MMIC) power amplifiers (PAs) with AlGaN/GaN high electronic mobility transistors (HEMTs) is presented. These high power amplifiers (HPAs) are based on a precise investigation of circuit-relevant HEMT behavior using two different field-plate variants and its effects on PA performance as well as optimization of HPA driver stage size which also has a deep impact on the entire HPA. Two broadband (3 GHz) MMICs with different field-plate variants and two narrowband (1 GHz) PAs with different driver- to final-stage gate-width ratio are realized with a maximum output power of 19-23 W, a maximum power-added efficiency (PAE) of ≥40%, and an associated power gain of 17 dB at X-band. Furthermore, two 1 mm test transistors of the same technology with the mentioned field-plate variants and a 1 mm test MMIC support VSWR-ratio tests of 6:1 and 4:1, respectively.
Fisz, Jacek J
2006-12-07
The optimization approach based on the genetic algorithm (GA) combined with multiple linear regression (MLR) method, is discussed. The GA-MLR optimizer is designed for the nonlinear least-squares problems in which the model functions are linear combinations of nonlinear functions. GA optimizes the nonlinear parameters, and the linear parameters are calculated from MLR. GA-MLR is an intuitive optimization approach and it exploits all advantages of the genetic algorithm technique. This optimization method results from an appropriate combination of two well-known optimization methods. The MLR method is embedded in the GA optimizer and linear and nonlinear model parameters are optimized in parallel. The MLR method is the only one strictly mathematical "tool" involved in GA-MLR. The GA-MLR approach simplifies and accelerates considerably the optimization process because the linear parameters are not the fitted ones. Its properties are exemplified by the analysis of the kinetic biexponential fluorescence decay surface corresponding to a two-excited-state interconversion process. A short discussion of the variable projection (VP) algorithm, designed for the same class of the optimization problems, is presented. VP is a very advanced mathematical formalism that involves the methods of nonlinear functionals, algebra of linear projectors, and the formalism of Fréchet derivatives and pseudo-inverses. Additional explanatory comments are added on the application of recently introduced the GA-NR optimizer to simultaneous recovery of linear and weakly nonlinear parameters occurring in the same optimization problem together with nonlinear parameters. The GA-NR optimizer combines the GA method with the NR method, in which the minimum-value condition for the quadratic approximation to chi(2), obtained from the Taylor series expansion of chi(2), is recovered by means of the Newton-Raphson algorithm. The application of the GA-NR optimizer to model functions which are multi
NASA Astrophysics Data System (ADS)
Djeffal, F.; Lakhdar, N.; Meguellati, M.; Benhaya, A.
2009-09-01
The analytical modeling of electron mobility in wurtzite Gallium Nitride (GaN) requires several simplifying assumptions, generally necessary to lead to compact expressions of electron transport characteristics for GaN-based devices. Further progress in the development, design and optimization of GaN-based devices necessarily requires new theory and modeling tools in order to improve the accuracy and the computational time of devices simulators. Recently, the evolutionary techniques, genetic algorithms ( GA) and particle swarm optimization ( PSO), have attracted considerable attention among various heuristic optimization techniques. In this paper, a particle swarm optimizer is implemented and compared to a genetic algorithm for modeling and optimization of new closed electron mobility model for GaN-based devices design. The performance of both optimization techniques in term of computational time and convergence rate is also compared. Further, our obtained results for both techniques ( PSO and GA) are tested and compared with numerical data (Monte Carlo simulations) where a good agreement has been found for wide range of temperature, doping and applied electric field. The developed analytical models can also be incorporated into the circuits simulators to study GaN-based devices without impact on the computational time and data storage.
Watrous, R.; Towell, G.; Glassman, M.S.
1995-12-31
Results are reported from the application of tools for synthesizing, optimizing and analyzing neural networks to an ECG Patient Monitoring task. A neural network was synthesized from a rule-based classifier and optimized over a set of normal and abnormal heartbeats. The classification error rate on a separate and larger test set was reduced by a factor of 2. When the network was analyzed and reduced in size by a factor of 40%, the same level of performance was maintained.
Application of a neural network to simulate analysis in an optimization process
NASA Technical Reports Server (NTRS)
Rogers, James L.; Lamarsh, William J., II
1992-01-01
A new experimental software package called NETS/PROSSS aimed at reducing the computing time required to solve a complex design problem is described. The software combines a neural network for simulating the analysis program with an optimization program. The neural network is applied to approximate results of a finite element analysis program to quickly obtain a near-optimal solution. Results of the NETS/PROSSS optimization process can also be used as an initial design in a normal optimization process and make it possible to converge to an optimum solution with significantly fewer iterations.
A two-layer recurrent neural network for nonsmooth convex optimization problems.
Qin, Sitian; Xue, Xiaoping
2015-06-01
In this paper, a two-layer recurrent neural network is proposed to solve the nonsmooth convex optimization problem subject to convex inequality and linear equality constraints. Compared with existing neural network models, the proposed neural network has a low model complexity and avoids penalty parameters. It is proved that from any initial point, the state of the proposed neural network reaches the equality feasible region in finite time and stays there thereafter. Moreover, the state is unique if the initial point lies in the equality feasible region. The equilibrium point set of the proposed neural network is proved to be equivalent to the Karush-Kuhn-Tucker optimality set of the original optimization problem. It is further proved that the equilibrium point of the proposed neural network is stable in the sense of Lyapunov. Moreover, from any initial point, the state is proved to be convergent to an equilibrium point of the proposed neural network. Finally, as applications, the proposed neural network is used to solve nonlinear convex programming with linear constraints and L1 -norm minimization problems.
NASA Technical Reports Server (NTRS)
Decker, Arthur J.
2001-01-01
Artificial neural networks have been used for a number of years to process holography-generated characteristic patterns of vibrating structures. This technology depends critically on the selection and the conditioning of the training sets. A scaling operation called folding is discussed for conditioning training sets optimally for training feed-forward neural networks to process characteristic fringe patterns. Folding allows feed-forward nets to be trained easily to detect damage-induced vibration-displacement-distribution changes as small as 10 nm. A specific application to aerospace of neural-net processing of characteristic patterns is presented to motivate the conditioning and optimization effort.
An optimized efficient dual junction InGaN/CIGS solar cell: A numerical simulation
NASA Astrophysics Data System (ADS)
Farhadi, Bita; Naseri, Mosayeb
2016-08-01
The photovoltaic performance of an efficient double junction InGaN/CIGS solar cell including a CdS antireflector top cover layer is studied using Silvaco ATLAS software. In this study, to gain a desired structure, the different design parameters, including the CIGS various band gaps, the doping concentration and the thickness of CdS layer are optimized. The simulation indicates that under current matching condition, an optimum efficiency of 40.42% is achieved.
NASA Astrophysics Data System (ADS)
Zhu, Bofan
Biocompatible scaffolds mimicking the locally aligned fibrous structure of native extracellular matrix (ECM) are in high demand in tissue engineering. In this thesis research, unidirectionally aligned fibers were generated via a home-built electrospinning system. Collagen type I, as a major ECM component, was chosen in this study due to its support of cell proliferation and promotion of neuroectodermal commitment in stem cell differentiation. Synthetic dragline silk proteins, as biopolymers with remarkable tensile strength and superior elasticity, were also used as a model material. Good alignment, controllable fiber size and morphology, as well as a desirable deposition density of fibers were achieved via the optimization of solution and electrospinning parameters. The incorporation of silk proteins into collagen was found to significantly enhance mechanical properties and stability of electrospun fibers. Glutaraldehyde (GA) vapor post-treatment was demonstrated as a simple and effective way to tune the properties of collagen/silk fibers without changing their chemical composition. With 6-12 hours GA treatment, electrospun collagen/silk fibers were not only biocompatible, but could also effectively induce the polarization and neural commitment of stem cells, which were optimized on collagen rich fibers due to the unique combination of biochemical and biophysical cues imposed to cells. Taken together, electrospun collagen rich composite fibers are mechanically strong, stable and provide excellent cell adhesion. The unidirectionally aligned fibers can accelerate neural differentiation of stem cells, representing a promising therapy for neural tissue degenerative diseases and nerve injuries.
Wu, Jianfa; Peng, Dahao; Li, Zhuping; Zhao, Li; Ling, Huanzhang
2015-01-01
To effectively and accurately detect and classify network intrusion data, this paper introduces a general regression neural network (GRNN) based on the artificial immune algorithm with elitist strategies (AIAE). The elitist archive and elitist crossover were combined with the artificial immune algorithm (AIA) to produce the AIAE-GRNN algorithm, with the aim of improving its adaptivity and accuracy. In this paper, the mean square errors (MSEs) were considered the affinity function. The AIAE was used to optimize the smooth factors of the GRNN; then, the optimal smooth factor was solved and substituted into the trained GRNN. Thus, the intrusive data were classified. The paper selected a GRNN that was separately optimized using a genetic algorithm (GA), particle swarm optimization (PSO), and fuzzy C-mean clustering (FCM) to enable a comparison of these approaches. As shown in the results, the AIAE-GRNN achieves a higher classification accuracy than PSO-GRNN, but the running time of AIAE-GRNN is long, which was proved first. FCM and GA-GRNN were eliminated because of their deficiencies in terms of accuracy and convergence. To improve the running speed, the paper adopted principal component analysis (PCA) to reduce the dimensions of the intrusive data. With the reduction in dimensionality, the PCA-AIAE-GRNN decreases in accuracy less and has better convergence than the PCA-PSO-GRNN, and the running speed of the PCA-AIAE-GRNN was relatively improved. The experimental results show that the AIAE-GRNN has a higher robustness and accuracy than the other algorithms considered and can thus be used to classify the intrusive data.
Wu, Jianfa; Peng, Dahao; Li, Zhuping; Zhao, Li; Ling, Huanzhang
2015-01-01
To effectively and accurately detect and classify network intrusion data, this paper introduces a general regression neural network (GRNN) based on the artificial immune algorithm with elitist strategies (AIAE). The elitist archive and elitist crossover were combined with the artificial immune algorithm (AIA) to produce the AIAE-GRNN algorithm, with the aim of improving its adaptivity and accuracy. In this paper, the mean square errors (MSEs) were considered the affinity function. The AIAE was used to optimize the smooth factors of the GRNN; then, the optimal smooth factor was solved and substituted into the trained GRNN. Thus, the intrusive data were classified. The paper selected a GRNN that was separately optimized using a genetic algorithm (GA), particle swarm optimization (PSO), and fuzzy C-mean clustering (FCM) to enable a comparison of these approaches. As shown in the results, the AIAE-GRNN achieves a higher classification accuracy than PSO-GRNN, but the running time of AIAE-GRNN is long, which was proved first. FCM and GA-GRNN were eliminated because of their deficiencies in terms of accuracy and convergence. To improve the running speed, the paper adopted principal component analysis (PCA) to reduce the dimensions of the intrusive data. With the reduction in dimensionality, the PCA-AIAE-GRNN decreases in accuracy less and has better convergence than the PCA-PSO-GRNN, and the running speed of the PCA-AIAE-GRNN was relatively improved. The experimental results show that the AIAE-GRNN has a higher robustness and accuracy than the other algorithms considered and can thus be used to classify the intrusive data. PMID:25807466
Optimization of multilayer neural network parameters for speaker recognition
NASA Astrophysics Data System (ADS)
Tovarek, Jaromir; Partila, Pavol; Rozhon, Jan; Voznak, Miroslav; Skapa, Jan; Uhrin, Dominik; Chmelikova, Zdenka
2016-05-01
This article discusses the impact of multilayer neural network parameters for speaker identification. The main task of speaker identification is to find a specific person in the known set of speakers. It means that the voice of an unknown speaker (wanted person) belongs to a group of reference speakers from the voice database. One of the requests was to develop the text-independent system, which means to classify wanted person regardless of content and language. Multilayer neural network has been used for speaker identification in this research. Artificial neural network (ANN) needs to set parameters like activation function of neurons, steepness of activation functions, learning rate, the maximum number of iterations and a number of neurons in the hidden and output layers. ANN accuracy and validation time are directly influenced by the parameter settings. Different roles require different settings. Identification accuracy and ANN validation time were evaluated with the same input data but different parameter settings. The goal was to find parameters for the neural network with the highest precision and shortest validation time. Input data of neural networks are a Mel-frequency cepstral coefficients (MFCC). These parameters describe the properties of the vocal tract. Audio samples were recorded for all speakers in a laboratory environment. Training, testing and validation data set were split into 70, 15 and 15 %. The result of the research described in this article is different parameter setting for the multilayer neural network for four speakers.
ELITE: ensemble of optimal input-pruned neural networks using TRUST-TECH.
Wang, Bin; Chiang, Hsiao-Dong
2011-01-01
The ensemble of optimal input-pruned neural networks using TRUST-TECH (ELITE) method for constructing high-quality ensemble through an optimal linear combination of accurate and diverse neural networks is developed. The optimization problems in the proposed methodology are solved by a global optimization a global optimization method called TRansformation Under Stability-reTraining Equilibrium Characterization (TRUST-TECH), whose main features include its capability in identifying multiple local optimal solutions in a deterministic, systematic, and tier-by-tier manner. ELITE creates a diverse population via a feature selection procedure of different local optimal neural networks obtained using tier-1 TRUST-TECH search. In addition, the capability of each input-pruned network is fully exploited through a TRUST-TECH-based optimal training. Finally, finding the optimal linear combination weights for an ensemble is modeled as a nonlinear programming problem and solved using TRUST-TECH and the interior point method, where the issue of non-convexity can be effectively handled. Extensive numerical experiments have been carried out for pattern classification on the synthetic and benchmark datasets. Numerical results show that ELITE consistently outperforms existing methods on the benchmark datasets. The results show that ELITE can be very promising for constructing high-quality neural network ensembles.
Optimization design on breakdown voltage of AlGaN/GaN high-electron mobility transistor
NASA Astrophysics Data System (ADS)
Yang, Liu; Changchun, Chai; Chunlei, Shi; Qingyang, Fan; Yuqian, Liu
2016-12-01
Simulations are carried out to explore the possibility of achieving high breakdown voltage of GaN HEMT (high-electron mobility transistor). GaN cap layers with gradual increase in the doping concentration from 2 × 1016 to 5 × 1019 cm-3 of N-type and P-type cap are investigated, respectively. Simulation results show that HEMT with P-doped GaN cap layer shows more potential to achieve higher breakdown voltage than N-doped GaN cap layer under the same doping concentration. This is because the ionized net negative space charges in P-GaN cap layer could modulate the surface electric field which makes more contribution to RESURF effect. Furthermore, a novel GaN/AlGaN/GaN HEMT with P-doped GaN buried layer in GaN buffer between gate and drain electrode is proposed. It shows enhanced performance. The breakdown voltage of the proposed structure is 640 V which is increased by 12% in comparison to UID (un-intentionally doped) GaN/AlGaN/GaN HEMT. We calculated and analyzed the distribution of electrons' density. It is found that the depleted region is wider and electric field maximum value is induced at the left edge of buried layer. So the novel structure with P-doped GaN buried layer embedded in GaN buffer has the better improving characteristics of the power devices. Project supported by the National Basic Research Program of China (No. 2014CB339900) and the Open Fund of Key Laboratory of Complex Electromagnetic Environment Science and Technology, China Academy of Engineering Physics (No. 2015-0214.XY.K).
High uniform growth of 4-inch GaN wafer via flow field optimization by HVPE
NASA Astrophysics Data System (ADS)
Cheng, Yutian; Liu, Peng; Wu, Jiejun; Xiang, Yong; Chen, Xinjuan; Ji, Cheng; Yu, Tongjun; Zhang, Guoyi
2016-07-01
The uniformity of flow field inner the reactor plays a crucial role for hydride vapor phase epitaxy (HVPE) crystal growth and its more important for large scale substrate. A new nozzle structure was designed by adding a push and dilution (PD) gas pipe in the center of gas channels for a 4-inch HVPE (PD-HVPE) system. Experimental results showed that the thickness inhomogeneity of 46 μm 4-inch GaN layer could reach ±1.8% by optimizing PD gas, greatly improved from ±14% grown with conventional nozzle. The simulations of the internal flow field were consistent with our experiment, and the enhancement in uniformity should be attributed to the redistribution of GaCl and NH3 upon the wafer induced by PD pipe. The full width at half maximum (FWHM) of X-ray diffraction rocking curves for the 4-inch GaN film were about 224 and 200 arcsec for (002) and (102) reflection. The dislocation density of as-grown GaN was about 6.4×107 cm-2.
NASA Astrophysics Data System (ADS)
Jang, Seon-Ho; Jo, Yong-Ryun; Lee, Young-Woong; Kim, Sei-Min; Kim, Bong-Joong; Bae, Jae-Hyun; An, Huei-Chun; Jang, Ja-Soon
2015-05-01
We report a highly transparent conducting electrode (TCE) scheme of MgxZn1-xO:Ga/Au/NiOx which was deposited on p-GaN by e-beam for GaN-based light emitting diodes (LEDs). The optical and electrical properties of the electrode were optimized by thermal annealing at 500°C for 1 minute in N2 + O2 (5:3) ambient. The light transmittance at the optimal condition increased up to 84-97% from the UV-A to yellow region. The specific contact resistance decreased to 4.3(±0.3) × 10-5 Ωcm2. The improved properties of the electrode were attributed to the directionally elongated crystalline nanostructures formed in the MgxZn1-xO:Ga layer which is compositionally uniform. Interestingly, the Au alloy nano-clusters created in the MgxZn1-xO:Ga layer during annealing at 500°C may also enhance the properties of the electrode by acting as a conducting bridge and a nano-sized mirror. Based on studies of the external quantum efficiency of blue LED devices, the proposed electrode scheme combined with an optimized annealing treatment suggests a potential alternative to ITO. [Figure not available: see fulltext.
High-Lift Optimization Design Using Neural Networks on a Multi-Element Airfoil
NASA Technical Reports Server (NTRS)
Greenman, Roxana M.; Roth, Karlin R.; Smith, Charles A. (Technical Monitor)
1998-01-01
The high-lift performance of a multi-element airfoil was optimized by using neural-net predictions that were trained using a computational data set. The numerical data was generated using a two-dimensional, incompressible, Navier-Stokes algorithm with the Spalart-Allmaras turbulence model. Because it is difficult to predict maximum lift for high-lift systems, an empirically-based maximum lift criteria was used in this study to determine both the maximum lift and the angle at which it occurs. Multiple input, single output networks were trained using the NASA Ames variation of the Levenberg-Marquardt algorithm for each of the aerodynamic coefficients (lift, drag, and moment). The artificial neural networks were integrated with a gradient-based optimizer. Using independent numerical simulations and experimental data for this high-lift configuration, it was shown that this design process successfully optimized flap deflection, gap, overlap, and angle of attack to maximize lift. Once the neural networks were trained and integrated with the optimizer, minimal additional computer resources were required to perform optimization runs with different initial conditions and parameters. Applying the neural networks within the high-lift rigging optimization process reduced the amount of computational time and resources by 83% compared with traditional gradient-based optimization procedures for multiple optimization runs.
InGaN/GaN multilayer quantum dots yellow-green light-emitting diode with optimized GaN barriers.
Lv, Wenbin; Wang, Lai; Wang, Jiaxing; Hao, Zhibiao; Luo, Yi
2012-11-07
InGaN/GaN multilayer quantum dot (QD) structure is a potential type of active regions for yellow-green light-emitting diodes (LEDs). The surface morphologies and crystalline quality of GaN barriers are critical to the uniformity of InGaN QD layers. While GaN barriers were grown in multi-QD layers, we used improved growth parameters by increasing the growth temperature and switching the carrier gas from N2 to H2 in the metal organic vapor phase epitaxy. As a result, a 10-layer InGaN/GaN QD LED is demonstrated successfully. The transmission electron microscopy image shows the uniform multilayer InGaN QDs clearly. As the injection current increases from 5 to 50 mA, the electroluminescence peak wavelength shifts from 574 to 537 nm.
InGaN/GaN multilayer quantum dots yellow-green light-emitting diode with optimized GaN barriers
2012-01-01
InGaN/GaN multilayer quantum dot (QD) structure is a potential type of active regions for yellow-green light-emitting diodes (LEDs). The surface morphologies and crystalline quality of GaN barriers are critical to the uniformity of InGaN QD layers. While GaN barriers were grown in multi-QD layers, we used improved growth parameters by increasing the growth temperature and switching the carrier gas from N2 to H2 in the metal organic vapor phase epitaxy. As a result, a 10-layer InGaN/GaN QD LED is demonstrated successfully. The transmission electron microscopy image shows the uniform multilayer InGaN QDs clearly. As the injection current increases from 5 to 50 mA, the electroluminescence peak wavelength shifts from 574 to 537 nm. PMID:23134721
NASA Technical Reports Server (NTRS)
Leong, Harrison Monfook
1988-01-01
General formulae for mapping optimization problems into systems of ordinary differential equations associated with artificial neural networks are presented. A comparison is made to optimization using gradient-search methods. The performance measure is the settling time from an initial state to a target state. A simple analytical example illustrates a situation where dynamical systems representing artificial neural network methods would settle faster than those representing gradient-search. Settling time was investigated for a more complicated optimization problem using computer simulations. The problem was a simplified version of a problem in medical imaging: determining loci of cerebral activity from electromagnetic measurements at the scalp. The simulations showed that gradient based systems typically settled 50 to 100 times faster than systems based on current neural network optimization methods.
NASA Technical Reports Server (NTRS)
Leong, Harrison Monfook
1988-01-01
General formulae for mapping optimization problems into systems of ordinary differential equations associated with artificial neural networks are presented. A comparison is made to optimization using gradient-search methods. The performance measure is the settling time from an initial state to a target state. A simple analytical example illustrates a situation where dynamical systems representing artificial neural network methods would settle faster than those representing gradient-search. Settling time was investigated for a more complicated optimization problem using computer simulations. The problem was a simplified version of a problem in medical imaging: determining loci of cerebral activity from electromagnetic measurements at the scalp. The simulations showed that gradient based systems typically settled 50 to 100 times faster than systems based on current neural network optimization methods.
Neural networks for process control and optimization: two industrial applications.
Bloch, Gérard; Denoeux, Thierry
2003-01-01
The two most widely used neural models, multilayer perceptron (MLP) and radial basis function network (RBFN), are presented in the framework of system identification and control. The main steps for building such nonlinear black box models are regressor choice, selection of internal architecture, and parameter estimation. The advantages of neural network models are summarized: universal approximation capabilities, flexibility, and parsimony. Two applications are described in steel industry and water treatment, respectively, the control of alloying process in a hot dipped galvanizing line and the control of a coagulation process in a drinking water treatment plant. These examples highlight the interest of neural techniques, when complex nonlinear phenomena are involved, but the empirical knowledge of control operators can be learned.
Predicting recurrent aphthous ulceration using genetic algorithms-optimized neural networks.
Dar-Odeh, Najla S; Alsmadi, Othman M; Bakri, Faris; Abu-Hammour, Zaer; Shehabi, Asem A; Al-Omiri, Mahmoud K; Abu-Hammad, Shatha M K; Al-Mashni, Hamzeh; Saeed, Mohammad B; Muqbil, Wael; Abu-Hammad, Osama A
2010-01-01
To construct and optimize a neural network that is capable of predicting the occurrence of recurrent aphthous ulceration (RAU) based on a set of appropriate input data. Artificial neural networks (ANN) software employing genetic algorithms to optimize the architecture neural networks was used. Input and output data of 86 participants (predisposing factors and status of the participants with regards to recurrent aphthous ulceration) were used to construct and train the neural networks. The optimized neural networks were then tested using untrained data of a further 10 participants. THE OPTIMIZED NEURAL NETWORK, WHICH PRODUCED THE MOST ACCURATE PREDICTIONS FOR THE PRESENCE OR ABSENCE OF RECURRENT APHTHOUS ULCERATION WAS FOUND TO EMPLOY: gender, hematological (with or without ferritin) and mycological data of the participants, frequency of tooth brushing, and consumption of vegetables and fruits. FACTORS APPEARING TO BE RELATED TO RECURRENT APHTHOUS ULCERATION AND APPROPRIATE FOR USE AS INPUT DATA TO CONSTRUCT ANNS THAT PREDICT RECURRENT APHTHOUS ULCERATION WERE FOUND TO INCLUDE THE FOLLOWING: gender, hemoglobin, serum vitamin B12, serum ferritin, red cell folate, salivary candidal colony count, frequency of tooth brushing, and the number of fruits or vegetables consumed daily.
Optimally doped hybridization gap semiconductor FeGa3 as potential thermoelectric alloy*
NASA Astrophysics Data System (ADS)
Ponnambalam, Vijayabarathi; Morelli, Donald T.
2014-03-01
FeGa3, a hybridization gap semiconductor with a band gap of ~ 0.5 eV can be a potential thermoelectric material if optimally doped. Due to the involvement of d-band in the transport, high Seebeck coefficient is a possibility. To achieve the optimum doping level, Mn, Co and Zn containing FeGa3 alloys are being prepared either via the flux or solid state reaction method. Phase characterization will be carried out. Electrical and transport properties including resistivity, Seebeck and Hall coefficients and thermal conductivity will be measured over a wide temperature range of 80- 1000 K. These results will be presented and the potential of these compositions as thermoelectrics will be discussed.
Material procedure quality forecast based on genetic BP neural network
NASA Astrophysics Data System (ADS)
Zheng, Bao-Hua
2017-07-01
Material procedure quality forecast plays an important role in quality control. This paper proposes a prediction model based on genetic algorithm (GA) and back propagation (BP) neural network. It can obtain the initial weights and thresholds of optimized BP neural network with the GA global search ability. A material process quality prediction model with the optimized BP neural network is adopted to predict the error of future process to measure the accuracy of process quality. The results show that the proposed method has the advantages of high accuracy and fast convergence rate compared with BP neural network.
Cost-optimal calculation for ice-storage systems using neural network
NASA Astrophysics Data System (ADS)
Hu, Zhihua; Qian, Huanqun; Zhang, Haipeng; Zhou, Fangde
2002-05-01
Based on the eminent characteristics of the ice-storage systems, which can shift cooling electrical demand from peak time to off peak time, this paper describes the ice storage air-conditioning system that is now used much frequently. The authors develop the operating cost model by simplification and introduce a neural network model and try to solve the optimal cost problem of operation by using this neural network model. In calculation, any trajectory of the neural network converges to its solution in finite time, which is consistent with result by simplex method. Comparing with different methods, the neural network is more effective, which can be alternative to simplex method in calculating the optimal cost model for ice storage air-conditioning systems.
Nezhadali, Azizollah; Motlagh, Maryam Omidvar; Sadeghzadeh, Samira
2017-09-13
A selective method based on molecularly imprinted polymer (MIP) solid-phase extraction (SPE) using UV-Vis spectrophotometry as a detection technique was developed for the determination of fluoxetine (FLU) in pharmaceutical and human serum samples. The MIPs were synthesized using pyrrole as a functional monomer in the presence of FLU as a template molecule. The factors that affecting the preparation and extraction ability of MIP such as amount of sorbent, initiator concentration, the amount of monomer to template ratio, uptake shaking rate, uptake time, washing buffer pH, take shaking rate, Taking time and polymerization time were considered for optimization. First a Plackett-Burman design (PBD) consists of 12 randomized runs were applied to determine the influence of each factor. The other optimization processes were performed using central composite design (CCD), artificial neural network (ANN) and genetic algorithm (GA). At optimal condition the calibration curve showed linearity over a concentration range of 10(-7)-10(-8)M with a correlation coefficient (R(2)) of 0.9970. The limit of detection (LOD) for FLU was obtained 6.56×10(-9)M. The repeatability of the method was obtained 1.61%. The synthesized MIP sorbent showed a good selectivity and sensitivity toward FLU. The MIP/SPE method was used for the determination of FLU in pharmaceutical, serum and plasma samples, successfully. Copyright © 2017 Elsevier B.V. All rights reserved.
ERIC Educational Resources Information Center
Nikelshpur, Dmitry O.
2014-01-01
Similar to mammalian brains, Artificial Neural Networks (ANN) are universal approximators, capable of yielding near-optimal solutions to a wide assortment of problems. ANNs are used in many fields including medicine, internet security, engineering, retail, robotics, warfare, intelligence control, and finance. "ANNs have a tendency to get…
ERIC Educational Resources Information Center
Nikelshpur, Dmitry O.
2014-01-01
Similar to mammalian brains, Artificial Neural Networks (ANN) are universal approximators, capable of yielding near-optimal solutions to a wide assortment of problems. ANNs are used in many fields including medicine, internet security, engineering, retail, robotics, warfare, intelligence control, and finance. "ANNs have a tendency to get…
Genetic learning in rule-based and neural systems
NASA Technical Reports Server (NTRS)
Smith, Robert E.
1993-01-01
The design of neural networks and fuzzy systems can involve complex, nonlinear, and ill-conditioned optimization problems. Often, traditional optimization schemes are inadequate or inapplicable for such tasks. Genetic Algorithms (GA's) are a class of optimization procedures whose mechanics are based on those of natural genetics. Mathematical arguments show how GAs bring substantial computational leverage to search problems, without requiring the mathematical characteristics often necessary for traditional optimization schemes (e.g., modality, continuity, availability of derivative information, etc.). GA's have proven effective in a variety of search tasks that arise in neural networks and fuzzy systems. This presentation begins by introducing the mechanism and theoretical underpinnings of GA's. GA's are then related to a class of rule-based machine learning systems called learning classifier systems (LCS's). An LCS implements a low-level production-system that uses a GA as its primary rule discovery mechanism. This presentation illustrates how, despite its rule-based framework, an LCS can be thought of as a competitive neural network. Neural network simulator code for an LCS is presented. In this context, the GA is doing more than optimizing and objective function. It is searching for an ecology of hidden nodes with limited connectivity. The GA attempts to evolve this ecology such that effective neural network performance results. The GA is particularly well adapted to this task, given its naturally-inspired basis. The LCS/neural network analogy extends itself to other, more traditional neural networks. Conclusions to the presentation discuss the implications of using GA's in ecological search problems that arise in neural and fuzzy systems.
Genetic learning in rule-based and neural systems
NASA Technical Reports Server (NTRS)
Smith, Robert E.
1993-01-01
The design of neural networks and fuzzy systems can involve complex, nonlinear, and ill-conditioned optimization problems. Often, traditional optimization schemes are inadequate or inapplicable for such tasks. Genetic Algorithms (GA's) are a class of optimization procedures whose mechanics are based on those of natural genetics. Mathematical arguments show how GAs bring substantial computational leverage to search problems, without requiring the mathematical characteristics often necessary for traditional optimization schemes (e.g., modality, continuity, availability of derivative information, etc.). GA's have proven effective in a variety of search tasks that arise in neural networks and fuzzy systems. This presentation begins by introducing the mechanism and theoretical underpinnings of GA's. GA's are then related to a class of rule-based machine learning systems called learning classifier systems (LCS's). An LCS implements a low-level production-system that uses a GA as its primary rule discovery mechanism. This presentation illustrates how, despite its rule-based framework, an LCS can be thought of as a competitive neural network. Neural network simulator code for an LCS is presented. In this context, the GA is doing more than optimizing and objective function. It is searching for an ecology of hidden nodes with limited connectivity. The GA attempts to evolve this ecology such that effective neural network performance results. The GA is particularly well adapted to this task, given its naturally-inspired basis. The LCS/neural network analogy extends itself to other, more traditional neural networks. Conclusions to the presentation discuss the implications of using GA's in ecological search problems that arise in neural and fuzzy systems.
The optimization of force inputs for active structural acoustic control using a neural network
NASA Technical Reports Server (NTRS)
Cabell, R. H.; Lester, H. C.; Silcox, R. J.
1992-01-01
This paper investigates the use of a neural network to determine which force actuators, of a multi-actuator array, are best activated in order to achieve structural-acoustic control. The concept is demonstrated using a cylinder/cavity model on which the control forces, produced by piezoelectric actuators, are applied with the objective of reducing the interior noise. A two-layer neural network is employed and the back propagation solution is compared with the results calculated by a conventional, least-squares optimization analysis. The ability of the neural network to accurately and efficiently control actuator activation for interior noise reduction is demonstrated.
NASA Astrophysics Data System (ADS)
Liew, C. K.; Veidt, M.
2007-03-01
Neural network pattern recognition is an advanced regression technique that can be applied to identify guided wave response signals for quantifying damages in structures. This paper describes a procedure to optimize the design of a multi-layer perceptron backpropagation neural network with signals preprocessed by the wavelet transform. The performance can be further improved using a weight-range selection technique in a series network since there is increased sensitivity of the neural network to experimental damage patterns if the training range is reduced. Damage identification in beams with longitudinal guided waves is used in this study.
Optimization of head movement recognition using Augmented Radial Basis Function Neural Network.
Yuwono, Mitchell; Handojoseno, A M Ardi; Nguyen, H T
2011-01-01
For people with severe spine injury, head movement recognition control has been proven to be one of the most convenient and intuitive ways to control a power wheelchair. While substantial research has been done in this area, the challenge to improve system reliability and accuracy remains due to the diversity in movement tendencies and the presence of movement artifacts. We propose a Neural-Network Configuration which we call Augmented Radial Basis Function Neural-Network (ARBF-NN). This network is constructed as a Radial Basis Function Neural-Network (RBF-NN) with a Multilayer Perceptron (MLP) augmentation layer to negate optimization limitation posed by linear classifiers in conventional RBF-NN. The RBF centroid is optimized through Regrouping Particle Swarm Optimization (RegPSO) seeded with K-Means. The trial results of ARBF-NN on Head-movement show a significant improvement on recognition accuracy up to 98.1% in sensitivity.
NASA Technical Reports Server (NTRS)
Jules, Kenol; Lin, Paul P.
2002-01-01
This paper reviews some of the recent applications of artificial neural networks taken from various works performed by the authors over the last four years at the NASA Glenn Research Center. This paper focuses mainly on two areas. First, artificial neural networks application in design and optimization of aircraft/engine propulsion systems to shorten the overall design cycle. Out of that specific application, a generic design tool was developed, which can be used for most design optimization process. Second, artificial neural networks application in monitoring the microgravity quality onboard the International Space Station, using on-board accelerometers for data acquisition. These two different applications are reviewed in this paper to show the broad applicability of artificial intelligence in various disciplines. The intent of this paper is not to give in-depth details of these two applications, but to show the need to combine different artificial intelligence techniques or algorithms in order to design an optimized or versatile system.
Experimentally-implemented genetic algorithm (Exp-GA): toward fully optimal photovoltaics.
Zhong, Yan Kai; Fu, Sze Ming; Ju, Nyan Ping; Chen, Po Yu; Lin, Albert
2015-09-21
The geometry and dimension design is the most critical part for the success in nano-photonic devices. The choices of the geometrical parameters dramatically affect the device performance. Most of the time, simulation is conducted to locate the suitable geometry, but in many cases simulation can be ineffective. The most pronounced examples are large-area randomized patterns for solar cells, light emitting diode (LED), and thermophtovoltaics (TPV). The large random pattern is nearly impossible to calculate and optimize due to the extended CPU runtime and the memory limitation. Other scenarios that numerical simulations become ineffective include three-dimensional complex structures with anisotropic dielectric response. This leads to extended simulation time especially for the repeated runs during its geometry optimization. In this paper, we show that by incorporating genetic algorithm (GA) into real-world experiments, shortened trial-and-error time can be achieved. More importantly, this scheme can be used for many photonic design problems that are unsuitable for simulation-based optimizations. Moreover, the experimentally implemented genetic algorithm (Exp-GA) has the additional advantage that the resultant objective value is a real one rather than a theoretical one. This prevents the gaps between the modeling and the fabrication due to the process variation or inaccurate numerical models. Using TPV emitters as an example, 22% enhancement in the mean objective value is achieved.
Exemplar-Based Policy with Selectable Strategies and its Optimization Using GA
NASA Astrophysics Data System (ADS)
Ikeda, Kokolo; Kobayashi, Shigenobu; Kita, Hajime
As an approach for dynamic control problems and decision making problems, usually formulated as Markov Decision Processes (MDPs), we focus direct policy search (DPS), where a policy is represented by a model with parameters, and the parameters are optimized so as to maximize the evaluation function by applying the parameterized policy to the problem. In this paper, a novel framework for DPS, an exemplar-based policy optimization using genetic algorithm (EBP-GA) is presented and analyzed. In this approach, the policy is composed of a set of virtual exemplars and a case-based action selector, and the set of exemplars are selected and evolved by a genetic algorithm. Here, an exemplar is a real or virtual, free-styled and suggestive information such as ``take the action A at the state S'' or ``the state S1 is better to attain than S2''. One advantage of EBP-GA is the generalization and localization ability for policy expression, based on case-based reasoning methods. Another advantage is that both the introduction of prior knowledge and the extraction of knowledge after optimization are relatively straightforward. These advantages are confirmed through the proposal of two new policy expressions, experiments on two different problems and their analysis.
Guofa Shou; Han Yuan; Urbano, Diamond; Yoon-Hee Cha; Lei Ding
2016-08-01
Repetitive transcranial magnetic stimulation (rTMS) has been increasingly used for its potential treatment effects across diverse mental disorders. However, the treatment effect is elusive and the rate of positive responders is not high, which make it in great demand of optimizing rTMS protocols to improve the treatment effects and the rate. In this regard, neural activity guided optimization has indicated great potential in several neuroimaging studies. In this paper, we present our ongoing work on optimizing rTMS treatment of a balance disorder, i.e., Mal de Debarquement syndrome (MdDS), by investigating treatment-related EEG neural synchrony and functional connectivity changes. Motivated by our previous pilot study of rTMS on MdDS, we firstly applied a bilateral dorsolateral prefrontal cortex (DLPFC) rTMS protocol to evaluate its efficacy and the treatment-related neural responses via an independent component analysis (ICA)-based framework. Thereafter, guided by identified EEG neural synchrony and functional connectivity patterns, we proposed three potential stimulation targets covering posterior nodes of the default mode network (DMN), and implemented a new rTMS protocol by stimulating the target with the great symptoms relief. The preliminary clinical response data has indicated that the new rTMS protocol significantly increase the rate of positive responders and the degrees of the improvement. The present study demonstrates that it is promising to integrate EEG neural synchrony and functional connectivity into the optimization of rTMS protocols for different mental disorders.
NASA Astrophysics Data System (ADS)
Kim, Eunsu; Kim, Manseok; Kim, Jong-Wook
In this paper, a humanoid is simulated and implemented to walk up and down a staircase using the blending polynomial and genetic algorithm (GA). Both ascending and descending a staircase are scheduled by four steps. Each step mimics natural gait of human being and is easy to analyze and implement. Optimal trajectories of ten motors in a lower extremity of a humanoid are rigorously computed to simultaneously satisfy stability condition, walking constraints, and energy efficiency requirements. As an optimization method, GA is applied to search optimal trajectory parameters in blending polynomials. The feasibility of this approach will be validated by simulation with a small humanoid robot.
Optimized feed-forward neural-network algorithm trained for cyclotron-cavity modeling
NASA Astrophysics Data System (ADS)
Mohamadian, Masoumeh; Afarideh, Hossein; Ghergherehchi, Mitra
2017-01-01
The cyclotron cavity presented in this paper is modeled by a feed-forward neural network trained by the authors’ optimized back-propagation (BP) algorithm. The training samples were obtained from simulation results that are for a number of defined situations and parameters and were achieved parametrically using MWS CST software; furthermore, the conventional BP algorithm with different hidden-neuron numbers, structures, and other optimal parameters such as learning rate that are applied for our purpose was also used here. The present study shows that an optimized FFN can be used to estimate the cyclotron-model parameters with an acceptable error function. A neural network trained by an optimized algorithm therefore shows a proper approximation and an acceptable ability regarding the modeling of the proposed structure. The cyclotron-cavity parameter-modeling results demonstrate that an FNN that is trained by the optimized algorithm could be a suitable method for the estimation of the design parameters in this case.
Ab initio guided optimization of GaTe for radiation detection applications
NASA Astrophysics Data System (ADS)
Rocha Leão, Cedric; Lordi, Vincenzo
2011-10-01
The development of semiconductor-based radiation detectors that display high energy resolution while operating at room temperature is a pressing need for scientific applications as well as homeland security. Practice has proven that the real performance of materials in such applications is often hindered by intrinsic defects and accidental impurities. Experimental efforts to improve the properties of such materials are both time consuming and costly, since they rely largely on trial and error. In this paper, the properties of gallium telluride (GaTe)—a high-Z, moderate-band-gap semiconductor—are investigated for room-temperature radiation detection applications. Systematic theoretical modeling based on density functional theory calculations is used to suggest experimental processes to grow this semiconductor with optimal properties. The goal is to judiciously identify the most detrimental native defects and devise ways to minimize their occurrence as well as compensate their electronic impact on the crystal. The analysis suggests that material grown Ga rich would have significantly higher resistivity, carrier mobilities, and carrier lifetimes compared to Te-rich material. In addition, Ge doping and In doping can be effective for carrier compensation of the material. Doping with Ge can be especially effective, if the ambipolar nature of substitutional incorporation on both Ga and Te sites is exploited.
Radosavljević, S.; Radovanović, J. Milanović, V.; Tomić, S.
2014-07-21
We have described a method for structural parameters optimization of GaN/AlGaN multiple quantum well based up-converter for silicon solar cells. It involves a systematic tuning of individual step quantum wells by use of the genetic algorithm for global optimization. In quantum well structures, the up-conversion process can be achieved by utilizing nonlinear optical effects based on intersubband transitions. Both single and double step quantum wells have been tested in order to maximize the second order susceptibility derived from the density matrix formalism. The results obtained for single step wells proved slightly better and have been further pursued to obtain a more complex design, optimized for conversion of an entire range of incident photon energies.
NASA Astrophysics Data System (ADS)
Zhang, Guang-Zheng; Huang, De-Shuang
2004-12-01
Inter-residue contacts map prediction is one of the most important intermediate steps to the protein folding problem. In this paper, we focus on the problem of protein inter-residue contacts map prediction based on neural network technique. Firstly, we use a genetic algorithm (GA) to optimize the radial basis function widths and hidden centers of a radial basis function neural network (RBFNN), then a novel binary encoding scheme is employed to train the network for the purpose of learning and predicting the inter-residue contacts patterns of protein sequences got from the protein data bank (PDB). The experimental evidence indicates the utility of our proposed encoding strategy and GA optimized RBFNN. Moreover, the simulation results demonstrate that the network got a better performance for these proteins, whose residue length falls into the area of (100, 300), and the predicted accuracy with a contact threshold of 7 Å scores higher than the other 3 values with 5, 6, and 8 Å.
Optimal design of GaAs-based concentrator space solar cells for 100 AMO, 80 deg C operation
NASA Technical Reports Server (NTRS)
Goradia, C.; Ghalla-Goradia, M.; Curtis, H.
1984-01-01
Using a detailed computer code and reasonable values of electrical and optical material parameters from current published literature, parameter optimization studies were performed on three configurations of GaAs-based concentrator solar cells for 100 AMO, 80 C operation. These studies show the possibility of designing GaAs-based solar cells with efficiencies exceeding 22% at 100 AMO 80 C and probable efficiency degradation of less than 15% after a 70% reduction in diffusion length in each cell region.
Optimized biogas-fermentation by neural network control.
Holubar, P; Zani, L; Hager, M; Fröschl, W; Radak, Z; Braun, R
2003-01-01
In this work several feed-forward back-propagation neural networks (FFBP) were trained in order to model, and subsequently control, methane production in anaerobic digesters. To produce data for the training of the neural nets, four anaerobic continuous stirred tank reactors (CSTR) were operated in steady-state conditions at organic loading rates (Br) of about 2 kg x m(-3) x d(-1) chemical oxygen demand (COD), and disturbed by pulse-like increase of the organic loading rate. For the pulses additional carbon sources were added to the basic feed (surplus- and primary sludge) to simulate cofermentation and to increase the COD. Measured parameters were: gas composition, methane production rate, volatile fatty acid concentration, pH, redox potential, volatile suspended solids and COD of feed and effluent. A hierarchical system of neural nets was developed and embedded in a Decision Support System (DSS). A 3-3-1 FFBP simulated the pH with a regression coefficient of 0.82. A 9-3-3 FFBP simulated the volatile fatty acid concentration in the sludge with a regression coefficient of 0.86. And a 9-3-2 FFBP simulated the gas production and gas composition with a regression coefficient of 0.90 and 0.80 respectively. A lab-scale anaerobic CSTR controlled by this tool was able to maintain a methane concentration of about 60% at a rather high gas production rate of between 5 to 5.6 m3 x m(-3) x d(-1).
Implementing size-optimal discrete neural networks requires analog circuitry
Beiu, V.
1998-03-01
Neural networks (NNs) have been experimentally shown to be quite effective in many applications. This success has led researchers to undertake a rigorous analysis of the mathematical properties that enable them to perform so well. It has generated two directions of research: (i) to find existence/constructive proofs for what is now known as the universal approximation problem; (ii) to find tight bounds on the size needed by the approximation problem (or some particular cases). The paper will focus on both aspects, for the particular case when the functions to be implemented are Boolean.
Artificial neural networks in Space Station optimal attitude control
NASA Astrophysics Data System (ADS)
Kumar, Renjith R.; Seywald, Hans; Deshpande, Samir M.; Rahman, Zia
1992-08-01
Innovative techniques of using 'Artificial Neural Networks' (ANN) for improving the performance of the pitch axis attitude control system of Space Station Freedom using Control Moment Gyros (CMGs) are investigated. The first technique uses a feedforward ANN with multilayer perceptrons to obtain an on-line controller which improves the performance of the control system via a model following approach. The second techique uses a single layer feedforward ANN with a modified back propagation scheme to estimate the internal plant variations and the external disturbances separately. These estimates are then used to solve two differential Riccati equations to obtain time varying gains which improve the control system performance in successive orbits.
A neural network model for optimizing vowel recognition by cochlear implant listeners.
Chang, C H; Anderson, G T; Loizou, P C
2001-03-01
Due to the variability in performance among cochlear implant (CI) patients, it is becoming increasingly important to find ways to optimally fit patients with speech processing strategies. This paper proposes an approach based on neural networks, which can be used to automatically optimize the performance of CI patients. The neural network model is implemented in two stages. In the first stage, a neural network is trained to mimic the CI patient's performance on the vowel identification task. The trained neural network is then used in the second stage to adjust a free parameter to improve vowel recognition performance for each individual patient. The parameter examined in this study was a weighting function applied to the compressed channel amplitudes extracted from a 6-channel continuous interleaved sampling (CIS) strategy. Two types of weighting functions were examined, one which assumed channel interaction, and one which assumed no interaction between channels. Results showed that the neural network models closely matched the performance of five Med-EI/CIS-Link implant patients. The resulting weighting functions obtained after neural network training improved vowel performance, with the larger improvement (4%) attained by the weighting function which modeled channel interaction.
A neural network model of reliably optimized spike transmission.
Samura, Toshikazu; Ikegaya, Yuji; Sato, Yasuomi D
2015-06-01
We studied the detailed structure of a neuronal network model in which the spontaneous spike activity is correctly optimized to match the experimental data and discuss the reliability of the optimized spike transmission. Two stochastic properties of the spontaneous activity were calculated: the spike-count rate and synchrony size. The synchrony size, expected to be an important factor for optimization of spike transmission in the network, represents a percentage of observed coactive neurons within a time bin, whose probability approximately follows a power-law. We systematically investigated how these stochastic properties could matched to those calculated from the experimental data in terms of the log-normally distributed synaptic weights between excitatory and inhibitory neurons and synaptic background activity induced by the input current noise in the network model. To ensure reliably optimized spike transmission, the synchrony size as well as spike-count rate were simultaneously optimized. This required changeably balanced log-normal distributions of synaptic weights between excitatory and inhibitory neurons and appropriately amplified synaptic background activity. Our results suggested that the inhibitory neurons with a hub-like structure driven by intensive feedback from excitatory neurons were a key factor in the simultaneous optimization of the spike-count rate and synchrony size, regardless of different spiking types between excitatory and inhibitory neurons.
2012-01-01
Background Synchronized bursting activity (SBA) is a remarkable dynamical behavior in both ex vivo and in vivo neural networks. Investigations of the underlying structural characteristics associated with SBA are crucial to understanding the system-level regulatory mechanism of neural network behaviors. Results In this study, artificial pulsed neural networks were established using spike response models to capture fundamental dynamics of large scale ex vivo cortical networks. Network simulations with synaptic parameter perturbations showed the following two findings. (i) In a network with an excitatory ratio (ER) of 80-90%, its connective ratio (CR) was within a range of 10-30% when the occurrence of SBA reached the highest expectation. This result was consistent with the experimental observation in ex vivo neuronal networks, which were reported to possess a matured inhibitory synaptic ratio of 10-20% and a CR of 10-30%. (ii) No SBA occurred when a network does not contain any all-positive-interaction feedback loop (APFL) motif. In a neural network containing APFLs, the number of APFLs presented an optimal range corresponding to the maximal occurrence of SBA, which was very similar to the optimal CR. Conclusions In a neural network, the evolutionarily selected CR (10-30%) optimizes the occurrence of SBA, and APFL serves a pivotal network motif required to maximize the occurrence of SBA. PMID:22462685
Optimization of AlAs/AlGaAs quantum well heterostructures on on-axis and misoriented GaAs (111)B
NASA Astrophysics Data System (ADS)
Herzog, F.; Bichler, M.; Koblmüller, G.; Prabhu-Gaunkar, S.; Zhou, W.; Grayson, M.
2012-05-01
We report systematic growth optimization of high Al-content AlGaAs, AlAs, and associated modulation-doped quantum well (QW) heterostructures on on-axis and misoriented GaAs (111)B by molecular beam epitaxy. Growth temperatures TG > 690 °C and low As4 fluxes close to group III-rich growth significantly suppress twin defects in high-Al content AlGaAs on on-axis GaAs (111)B, as quantified by atomic force and transmission electron microscopy as well as x-ray diffraction. Mirror-smooth and defect-free AlAs with pronounced step-flow morphology was further achieved by growth on 2° misoriented GaAs (111)B toward [01¯1] and [21¯1¯] orientations. Successful fabrication of modulation-doped AlAs QW structures on these misoriented substrates yielded record electron mobilities (at 1.15 K) in excess of 13 000 cm2/Vs at sheet carrier densities of 5 × 1011 cm-2.
Huang, Daizheng; Wu, Zhihui
2017-01-01
Accurately predicting the trend of outpatient visits by mathematical modeling can help policy makers manage hospitals effectively, reasonably organize schedules for human resources and finances, and appropriately distribute hospital material resources. In this study, a hybrid method based on empirical mode decomposition and back-propagation artificial neural networks optimized by particle swarm optimization is developed to forecast outpatient visits on the basis of monthly numbers. The data outpatient visits are retrieved from January 2005 to December 2013 and first obtained as the original time series. Second, the original time series is decomposed into a finite and often small number of intrinsic mode functions by the empirical mode decomposition technique. Third, a three-layer back-propagation artificial neural network is constructed to forecast each intrinsic mode functions. To improve network performance and avoid falling into a local minimum, particle swarm optimization is employed to optimize the weights and thresholds of back-propagation artificial neural networks. Finally, the superposition of forecasting results of the intrinsic mode functions is regarded as the ultimate forecasting value. Simulation indicates that the proposed method attains a better performance index than the other four methods.
Huang, Daizheng; Wu, Zhihui
2017-01-01
Accurately predicting the trend of outpatient visits by mathematical modeling can help policy makers manage hospitals effectively, reasonably organize schedules for human resources and finances, and appropriately distribute hospital material resources. In this study, a hybrid method based on empirical mode decomposition and back-propagation artificial neural networks optimized by particle swarm optimization is developed to forecast outpatient visits on the basis of monthly numbers. The data outpatient visits are retrieved from January 2005 to December 2013 and first obtained as the original time series. Second, the original time series is decomposed into a finite and often small number of intrinsic mode functions by the empirical mode decomposition technique. Third, a three-layer back-propagation artificial neural network is constructed to forecast each intrinsic mode functions. To improve network performance and avoid falling into a local minimum, particle swarm optimization is employed to optimize the weights and thresholds of back-propagation artificial neural networks. Finally, the superposition of forecasting results of the intrinsic mode functions is regarded as the ultimate forecasting value. Simulation indicates that the proposed method attains a better performance index than the other four methods. PMID:28222194
Performance optimization of Pnp InGaAs/InP heterojunction phototransistors
NASA Astrophysics Data System (ADS)
Chen, Jun; Zhu, Min
2016-12-01
Fabrication, physical simulation, and optimization of two-terminal Pnp heterojunction phototransistors (2T-HPTs) based on In0.53Ga0.47As/InP are reported. The parameters of fundamental models are determined by comparing the simulated current and response characteristics with the experimental results. To optimize the optical gain and device performance, the precise adjustment of the base doping level, base width, and compositional grading of base has been investigated. Properly reducing the base width or increasing the range of the compositional grading can greatly enhance the emitter injection efficiency. The effects of high-low doping in collector region and the insertion of a thin, undoped InGaAs layer in the base region of the HPT have also been investigated in detail. It is found the high-low doping in collector can form an electric field to aid carrier transport, and the intrinsic layer between emitter and base has functions of reducing knee voltage and the dark current of HPT.
Orlowska-Kowalska, Teresa; Kaminski, Marcin
2014-01-01
The paper deals with the implementation of optimized neural networks (NNs) for state variable estimation of the drive system with an elastic joint. The signals estimated by NNs are used in the control structure with a state-space controller and additional feedbacks from the shaft torque and the load speed. High estimation quality is very important for the correct operation of a closed-loop system. The precision of state variables estimation depends on the generalization properties of NNs. A short review of optimization methods of the NN is presented. Two techniques typical for regularization and pruning methods are described and tested in detail: the Bayesian regularization and the Optimal Brain Damage methods. Simulation results show good precision of both optimized neural estimators for a wide range of changes of the load speed and the load torque, not only for nominal but also changed parameters of the drive system. The simulation results are verified in a laboratory setup.
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.
Artificial neural networks in evaluation and optimization of modified release solid dosage forms.
Ibrić, Svetlana; Djuriš, Jelena; Parojčić, Jelena; Djurić, Zorica
2012-10-18
Implementation of the Quality by Design (QbD) approach in pharmaceutical development has compelled researchers in the pharmaceutical industry to employ Design of Experiments (DoE) as a statistical tool, in product development. Among all DoE techniques, response surface methodology (RSM) is the one most frequently used. Progress of computer science has had an impact on pharmaceutical development as well. Simultaneous with the implementation of statistical methods, machine learning tools took an important place in drug formulation. Twenty years ago, the first papers describing application of artificial neural networks in optimization of modified release products appeared. Since then, a lot of work has been done towards implementation of new techniques, especially Artificial Neural Networks (ANN) in modeling of production, drug release and drug stability of modified release solid dosage forms. The aim of this paper is to review artificial neural networks in evaluation and optimization of modified release solid dosage forms.
Artificial Neural Networks in Evaluation and Optimization of Modified Release Solid Dosage Forms
Ibrić, Svetlana; Djuriš, Jelena; Parojčić, Jelena; Djurić, Zorica
2012-01-01
Implementation of the Quality by Design (QbD) approach in pharmaceutical development has compelled researchers in the pharmaceutical industry to employ Design of Experiments (DoE) as a statistical tool, in product development. Among all DoE techniques, response surface methodology (RSM) is the one most frequently used. Progress of computer science has had an impact on pharmaceutical development as well. Simultaneous with the implementation of statistical methods, machine learning tools took an important place in drug formulation. Twenty years ago, the first papers describing application of artificial neural networks in optimization of modified release products appeared. Since then, a lot of work has been done towards implementation of new techniques, especially Artificial Neural Networks (ANN) in modeling of production, drug release and drug stability of modified release solid dosage forms. The aim of this paper is to review artificial neural networks in evaluation and optimization of modified release solid dosage forms. PMID:24300369
Two-Dimensional High-Lift Aerodynamic Optimization Using Neural Networks
NASA Technical Reports Server (NTRS)
Greenman, Roxana M.
1998-01-01
The high-lift performance of a multi-element airfoil was optimized by using neural-net predictions that were trained using a computational data set. The numerical data was generated using a two-dimensional, incompressible, Navier-Stokes algorithm with the Spalart-Allmaras turbulence model. Because it is difficult to predict maximum lift for high-lift systems, an empirically-based maximum lift criteria was used in this study to determine both the maximum lift and the angle at which it occurs. The 'pressure difference rule,' which states that the maximum lift condition corresponds to a certain pressure difference between the peak suction pressure and the pressure at the trailing edge of the element, was applied and verified with experimental observations for this configuration. Multiple input, single output networks were trained using the NASA Ames variation of the Levenberg-Marquardt algorithm for each of the aerodynamic coefficients (lift, drag and moment). The artificial neural networks were integrated with a gradient-based optimizer. Using independent numerical simulations and experimental data for this high-lift configuration, it was shown that this design process successfully optimized flap deflection, gap, overlap, and angle of attack to maximize lift. Once the neural nets were trained and integrated with the optimizer, minimal additional computer resources were required to perform optimization runs with different initial conditions and parameters. Applying the neural networks within the high-lift rigging optimization process reduced the amount of computational time and resources by 44% compared with traditional gradient-based optimization procedures for multiple optimization runs.
Study on feed forward neural network convex optimization for LiFePO4 battery parameters
NASA Astrophysics Data System (ADS)
Liu, Xuepeng; Zhao, Dongmei
2017-08-01
Based on the modern facility agriculture automatic walking equipment LiFePO4 Battery, the parameter identification of LiFePO4 Battery is analyzed. An improved method for the process model of li battery is proposed, and the on-line estimation algorithm is presented. The parameters of the battery are identified using feed forward network neural convex optimization algorithm.
Artificial neural networks in Space Station optimal attitude control
NASA Astrophysics Data System (ADS)
Kumar, Renjith R.; Seywald, Hans; Deshpande, Samir M.; Rahman, Zia
1995-01-01
Innovative techniques of using "artificial neural networks" (ANN) for improving the performance of the pitch axis attitude control system of Space Station Freedom using control moment gyros (CMGs) are investigated. The first technique uses a feed-forward ANN with multi-layer perceptrons to obtain an on-line controller which improves the performance of the control system via a model following approach. The second technique uses a single layer feed-forward ANN with a modified back propagation scheme to estimate the internal plant variations and the external disturbances separately. These estimates are then used to solve two differential Riccati equations to obtain time varying gains which improve the control system performance in successive orbits.
A Subsonic Aircraft Design Optimization With Neural Network and Regression Approximators
NASA Technical Reports Server (NTRS)
Patnaik, Surya N.; Coroneos, Rula M.; Guptill, James D.; Hopkins, Dale A.; Haller, William J.
2004-01-01
The Flight-Optimization-System (FLOPS) code encountered difficulty in analyzing a subsonic aircraft. The limitation made the design optimization problematic. The deficiencies have been alleviated through use of neural network and regression approximations. The insight gained from using the approximators is discussed in this paper. The FLOPS code is reviewed. Analysis models are developed and validated for each approximator. The regression method appears to hug the data points, while the neural network approximation follows a mean path. For an analysis cycle, the approximate model required milliseconds of central processing unit (CPU) time versus seconds by the FLOPS code. Performance of the approximators was satisfactory for aircraft analysis. A design optimization capability has been created by coupling the derived analyzers to the optimization test bed CometBoards. The approximators were efficient reanalysis tools in the aircraft design optimization. Instability encountered in the FLOPS analyzer was eliminated. The convergence characteristics were improved for the design optimization. The CPU time required to calculate the optimum solution, measured in hours with the FLOPS code was reduced to minutes with the neural network approximation and to seconds with the regression method. Generation of the approximators required the manipulation of a very large quantity of data. Design sensitivity with respect to the bounds of aircraft constraints is easily generated.
NASA Astrophysics Data System (ADS)
He, Xiao-Guang; Zhao, De-Gang; Jiang, De-Sheng; Zhu, Jian-Jun; Chen, Ping; Liu, Zong-Shun; Le, Ling-Cong; Yang, Jing; Li, Xiao-Jing; Zhang, Shu-Ming; Yang, Hui
2015-09-01
AlGaN/AlN/GaN structures are grown by metalorganic vapor phase epitaxy on sapphire substrates. Influences of AlN interlayer thickness, AlGaN barrier thickness, and Al composition on the two-dimensional electron gas (2DEG) performance are investigated. Lowering the V/III ratio and enhancing the reactor pressure at the initial stage of the high-temperature GaN layer growth will prolong the GaN nuclei coalescence process and effectively improve the crystalline quality and the interface morphology, diminishing the interface roughness scattering and improving 2DEG mobility. AlGaN/AlN/GaN structure with 2DEG sheet density of 1.19 × 1013 cm-2, electron mobility of 2101 cm2·V-1·s-1, and square resistance of 249 Ω is obtained. Project support by the National Natural Science Foundation of China (Grant Nos. 61474110, 61377020, 61376089, 61223005, and 61176126), the National Science Fund for Distinguished Young Scholars, China (Grant No. 60925017), the One Hundred Person Project of the Chinese Academy of Sciences, and the Basic Research Project of Jiangsu Province, China (Grant No. BK20130362).
Zheng, Zi-Yi; Guo, Xiao-Na; Zhu, Ke-Xue; Peng, Wei; Zhou, Hui-Ming
2017-07-15
Methoxy-ρ-benzoquinone (MBQ) and 2, 6-dimethoxy-ρ-benzoquinone (DMBQ) are two potential anticancer compounds in fermented wheat germ. In present study, modeling and optimization of added macronutrients, microelements, vitamins for producing MBQ and DMBQ was investigated using artificial neural network (ANN) combined with genetic algorithm (GA). A configuration of 16-11-1 ANN model with Levenberg-Marquardt training algorithm was applied for modeling the complicated nonlinear interactions among 16 nutrients in fermentation process. Under the guidance of optimized scheme, the total contents of MBQ and DMBQ was improved by 117% compared with that in the control group. Further, by evaluating the relative importance of each nutrient in terms of the two benzoquinones' yield, macronutrients and microelements were found to have a greater influence than most of vitamins. It was also observed that a number of interactions between nutrients affected the yield of MBQ and DMBQ remarkably. Copyright © 2017 Elsevier Ltd. All rights reserved.
NASA Technical Reports Server (NTRS)
Hutchby, J. A.; Fudurich, R. L.
1976-01-01
A comprehensive theoretical model of the graded band-gap Al(x)Ga(1-x)As-GaAs solar cell is used to optimize the n-on-p cell. The model includes power losses due to surface, bulk, and junction minority-carrier recombination, series resistance, and photon reflection from an SiO antireflection coating of optimum thickness. The optimized cell has a junction depth/graded band-gap layer thickness of 1.0 micron, respective donor and acceptor concentrations of 4 x 10 to the 17th power and 2 x 10 to the 17th power per cu cm, and a surface AlAs mode fraction of x = 0.35. The optimized graded band-gap cell has an air-mass-zero efficiency of 17.7% (not corrected for a 13% front surface contact area) and is shown to be less sensitive than a similar n-on-p GaAs cell to material degradation in the form of decreased minority-carrier diffusion lengths and increased surface-recombination velocity
NASA Technical Reports Server (NTRS)
Hutchby, J. A.; Fudurich, R. L.
1976-01-01
A comprehensive theoretical model of the graded band-gap Al(x)Ga(1-x)As-GaAs solar cell is used to optimize the n-on-p cell. The model includes power losses due to surface, bulk, and junction minority-carrier recombination, series resistance, and photon reflection from an SiO antireflection coating of optimum thickness. The optimized cell has a junction depth/graded band-gap layer thickness of 1.0 micron, respective donor and acceptor concentrations of 4 x 10 to the 17th power and 2 x 10 to the 17th power per cu cm, and a surface AlAs mode fraction of x = 0.35. The optimized graded band-gap cell has an air-mass-zero efficiency of 17.7% (not corrected for a 13% front surface contact area) and is shown to be less sensitive than a similar n-on-p GaAs cell to material degradation in the form of decreased minority-carrier diffusion lengths and increased surface-recombination velocity
NASA Technical Reports Server (NTRS)
Berke, Laszlo; Patnaik, Surya N.; Murthy, Pappu L. N.
1993-01-01
The application of artificial neural networks to capture structural design expertise is demonstrated. The principal advantage of a trained neural network is that it requires trivial computational effort to produce an acceptable new design. For the class of problems addressed, the development of a conventional expert system would be extremely difficult. In the present effort, a structural optimization code with multiple nonlinear programming algorithms and an artificial neural network code NETS were used. A set of optimum designs for a ring and two aircraft wings for static and dynamic constraints were generated by using the optimization codes. The optimum design data were processed to obtain input and output pairs, which were used to develop a trained artificial neural network with the code NETS. Optimum designs for new design conditions were predicted by using the trained network. Neural net prediction of optimum designs was found to be satisfactory for most of the output design parameters. However, results from the present study indicate that caution must be exercised to ensure that all design variables are within selected error bounds.
Toward an optimal convolutional neural network for traffic sign recognition
NASA Astrophysics Data System (ADS)
Habibi Aghdam, Hamed; Jahani Heravi, Elnaz; Puig, Domenec
2015-12-01
Convolutional Neural Networks (CNN) beat the human performance on German Traffic Sign Benchmark competition. Both the winner and the runner-up teams trained CNNs to recognize 43 traffic signs. However, both networks are not computationally efficient since they have many free parameters and they use highly computational activation functions. In this paper, we propose a new architecture that reduces the number of the parameters 27% and 22% compared with the two networks. Furthermore, our network uses Leaky Rectified Linear Units (ReLU) as the activation function that only needs a few operations to produce the result. Specifically, compared with the hyperbolic tangent and rectified sigmoid activation functions utilized in the two networks, Leaky ReLU needs only one multiplication operation which makes it computationally much more efficient than the two other functions. Our experiments on the Gertman Traffic Sign Benchmark dataset shows 0:6% improvement on the best reported classification accuracy while it reduces the overall number of parameters 85% compared with the winner network in the competition.
Study on Optimized Elman Neural Network Classification Algorithm Based on PLS and CA
Zhao, Dean; Shen, Tian; Zhao, Yuyan
2014-01-01
High-dimensional large sample data sets, between feature variables and between samples, may cause some correlative or repetitive factors, occupy lots of storage space, and consume much computing time. Using the Elman neural network to deal with them, too many inputs will influence the operating efficiency and recognition accuracy; too many simultaneous training samples, as well as being not able to get precise neural network model, also restrict the recognition accuracy. Aiming at these series of problems, we introduce the partial least squares (PLS) and cluster analysis (CA) into Elman neural network algorithm, by the PLS for dimension reduction which can eliminate the correlative and repetitive factors of the features. Using CA eliminates the correlative and repetitive factors of the sample. If some subclass becomes small sample, with high-dimensional feature and fewer numbers, PLS shows a unique advantage. Each subclass is regarded as one training sample to train the different precise neural network models. Then simulation samples are discriminated and classified into different subclasses, using the corresponding neural network to recognize it. An optimized Elman neural network classification algorithm based on PLS and CA (PLS-CA-Elman algorithm) is established. The new algorithm aims at improving the operating efficiency and recognition accuracy. By the case analysis, the new algorithm has unique superiority, worthy of further promotion. PMID:25165470
Study on optimized Elman neural network classification algorithm based on PLS and CA.
Jia, Weikuan; Zhao, Dean; Shen, Tian; Tang, Yuyang; Zhao, Yuyan
2014-01-01
High-dimensional large sample data sets, between feature variables and between samples, may cause some correlative or repetitive factors, occupy lots of storage space, and consume much computing time. Using the Elman neural network to deal with them, too many inputs will influence the operating efficiency and recognition accuracy; too many simultaneous training samples, as well as being not able to get precise neural network model, also restrict the recognition accuracy. Aiming at these series of problems, we introduce the partial least squares (PLS) and cluster analysis (CA) into Elman neural network algorithm, by the PLS for dimension reduction which can eliminate the correlative and repetitive factors of the features. Using CA eliminates the correlative and repetitive factors of the sample. If some subclass becomes small sample, with high-dimensional feature and fewer numbers, PLS shows a unique advantage. Each subclass is regarded as one training sample to train the different precise neural network models. Then simulation samples are discriminated and classified into different subclasses, using the corresponding neural network to recognize it. An optimized Elman neural network classification algorithm based on PLS and CA (PLS-CA-Elman algorithm) is established. The new algorithm aims at improving the operating efficiency and recognition accuracy. By the case analysis, the new algorithm has unique superiority, worthy of further promotion.
NASA Technical Reports Server (NTRS)
Patniak, Surya N.; Guptill, James D.; Hopkins, Dale A.; Lavelle, Thomas M.
1998-01-01
Nonlinear mathematical-programming-based design optimization can be an elegant method. However, the calculations required to generate the merit function, constraints, and their gradients, which are frequently required, can make the process computational intensive. The computational burden can be greatly reduced by using approximating analyzers derived from an original analyzer utilizing neural networks and linear regression methods. The experience gained from using both of these approximation methods in the design optimization of a high speed civil transport aircraft is the subject of this paper. The Langley Research Center's Flight Optimization System was selected for the aircraft analysis. This software was exercised to generate a set of training data with which a neural network and a regression method were trained, thereby producing the two approximating analyzers. The derived analyzers were coupled to the Lewis Research Center's CometBoards test bed to provide the optimization capability. With the combined software, both approximation methods were examined for use in aircraft design optimization, and both performed satisfactorily. The CPU time for solution of the problem, which had been measured in hours, was reduced to minutes with the neural network approximation and to seconds with the regression method. Instability encountered in the aircraft analysis software at certain design points was also eliminated. On the other hand, there were costs and difficulties associated with training the approximating analyzers. The CPU time required to generate the input-output pairs and to train the approximating analyzers was seven times that required for solution of the problem.
Wang, Jie-sheng; Li, Shu-xia; Gao, Jie
2014-01-01
For meeting the real-time fault diagnosis and the optimization monitoring requirements of the polymerization kettle in the polyvinyl chloride resin (PVC) production process, a fault diagnosis strategy based on the self-organizing map (SOM) neural network is proposed. Firstly, a mapping between the polymerization process data and the fault pattern is established by analyzing the production technology of polymerization kettle equipment. The particle swarm optimization (PSO) algorithm with a new dynamical adjustment method of inertial weights is adopted to optimize the structural parameters of SOM neural network. The fault pattern classification of the polymerization kettle equipment is to realize the nonlinear mapping from symptom set to fault set according to the given symptom set. Finally, the simulation experiments of fault diagnosis are conducted by combining with the industrial on-site historical data of the polymerization kettle and the simulation results show that the proposed PSO-SOM fault diagnosis strategy is effective. PMID:25152929
Wang, Jie-sheng; Li, Shu-xia; Gao, Jie
2014-01-01
For meeting the real-time fault diagnosis and the optimization monitoring requirements of the polymerization kettle in the polyvinyl chloride resin (PVC) production process, a fault diagnosis strategy based on the self-organizing map (SOM) neural network is proposed. Firstly, a mapping between the polymerization process data and the fault pattern is established by analyzing the production technology of polymerization kettle equipment. The particle swarm optimization (PSO) algorithm with a new dynamical adjustment method of inertial weights is adopted to optimize the structural parameters of SOM neural network. The fault pattern classification of the polymerization kettle equipment is to realize the nonlinear mapping from symptom set to fault set according to the given symptom set. Finally, the simulation experiments of fault diagnosis are conducted by combining with the industrial on-site historical data of the polymerization kettle and the simulation results show that the proposed PSO-SOM fault diagnosis strategy is effective.
Design Optimization for Suspension System of High Speed Train Using Neural Network
NASA Astrophysics Data System (ADS)
Kim, Young-Guk; Park, Chan-Kyoung; Hwang, Hee-Soo; Park, Tae-Won
Design optimization has been performed for the suspension system of high speed train. Neural network and design of experiment (DOE) have been employed to build a meta-model for the system with 29 design variables and 46 responses. A combination of fractional factorial design and D-optimality design was used as an approach to DOE in order to reduce the number of experiments to a more practical level. As a result, only 66 experiments were enough. The 46 responses were divided into four performance index groups such as ride comfort, derailment quotient, unloading ratio and stability index. Four meta-models for each index group were constructed by use of neural network. For the learned meta-models, multi-criteria optimization was achieved by differential evolution. The results show that the proposed methodology yields a highly improved design in the ride comfort, unloading ratio and stability index.
Two neural network algorithms for designing optimal terminal controllers with open final time
NASA Technical Reports Server (NTRS)
Plumer, Edward S.
1992-01-01
Multilayer neural networks, trained by the backpropagation through time algorithm (BPTT), have been used successfully as state-feedback controllers for nonlinear terminal control problems. Current BPTT techniques, however, are not able to deal systematically with open final-time situations such as minimum-time problems. Two approaches which extend BPTT to open final-time problems are presented. In the first, a neural network learns a mapping from initial-state to time-to-go. In the second, the optimal number of steps for each trial run is found using a line-search. Both methods are derived using Lagrange multiplier techniques. This theoretical framework is used to demonstrate that the derived algorithms are direct extensions of forward/backward sweep methods used in N-stage optimal control. The two algorithms are tested on a Zermelo problem and the resulting trajectories compare favorably to optimal control results.
Optimization of p-doping in AlGaAs grown by CBE using TMA for AlGaAs/GaAs tunnel junctions
NASA Astrophysics Data System (ADS)
Paquette, Bernard; DeVita, Marie; Turala, Artur; Kolhatkar, Gitanjali; Boucherif, Abderraouf; Jaouad, Abdelatif; Aimez, Vincent; Arès, Richard
2013-07-01
Trimethyl aluminium (TMA) was used as an intrinsic dopant source to grow highly p-doped AlGaAs by chemical beam epitaxy (CBE). Growth parameters were varied to control doping level, and three sets of growth parameters were identified to maximize the hole concentration in CBE-grown AlGaAs: low temperature growth; low V/III ratio combined with high growth rate; aluminium-rich composition. AlGaAs/GaAs tunnel junctions were fabricated using each of these set of growth parameters and tunneling peak currents as high as 6136 A/cm2 were obtained. These tunnel junctions are suitable for use in very high concentration multijunction solar cells.
Optimization of cocoa butter analog synthesis variables using neural networks and genetic algorithm.
Shekarchizadeh, Hajar; Tikani, Reza; Kadivar, Mahdi
2014-09-01
Cocoa butter analog was prepared from camel hump fat and tristearin by enzymatic interesterification in supercritical carbon dioxide (SC-CO2) using immobilized Thermomyces lanuginosus lipase (Lipozyme TL IM) as a biocatalyst. Optimal process conditions were determined using neural networks and genetic algorithm optimization. Response surfaces methodology was used to design the experiments to collect data for the neural network modelling. A general regression neural network model was developed to predict the response of triacylglycerol (TAG) distribution of cocoa butter analog from the process pressure, temperature, tristearin/camel hump fat ratio, water content, and incubation time. A genetic algorithm was used to search for a combination of the process variables for production of most similar cocoa butter analog to the corresponding cocoa butter. The combinations of the process variables during genetic algorithm optimization were evaluated using the neural network model. The pressure of 10 MPa; temperature of 40 °C; SSS/CHF ratio of 0.6:1; water content of 13 % (w/w); and incubation time of 4.5 h were found to be the optimum conditions to achieve the most similar cocoa butter analog to the corresponding cocoa butter.
Optimization behavior of brainstem respiratory neurons. A cerebral neural network model.
Poon, C S
1991-01-01
A recent model of respiratory control suggested that the steady-state respiratory responses to CO2 and exercise may be governed by an optimal control law in the brainstem respiratory neurons. It was not certain, however, whether such complex optimization behavior could be accomplished by a realistic biological neural network. To test this hypothesis, we developed a hybrid computer-neural model in which the dynamics of the lung, brain and other tissue compartments were simulated on a digital computer. Mimicking the "controller" was a human subject who pedalled on a bicycle with varying speed (analog of ventilatory output) with a view to minimize an analog signal of the total cost of breathing (chemical and mechanical) which was computed interactively and displayed on an oscilloscope. In this manner, the visuomotor cortex served as a proxy (homolog) of the brainstem respiratory neurons in the model. Results in 4 subjects showed a linear steady-state ventilatory CO2 response to arterial PCO2 during simulated CO2 inhalation and a nearly isocapnic steady-state response during simulated exercise. Thus, neural optimization is a plausible mechanism for respiratory control during exercise and can be achieved by a neural network with cognitive computational ability without the need for an exercise stimulus.
A high-performance keyboard neural prosthesis enabled by task optimization
Nuyujukian, Paul; Fan, Joline M.; Kao, Jonathan C.; Ryu, Stephen I.; Shenoy, Krishna V.
2015-01-01
Communication neural prostheses are an emerging class of medical devices that aim to restore efficient communication to people suffering from paralysis. These systems rely on an interface with the user, either via the use of a continuously-moving cursor (e.g., mouse) or the discrete selection of symbols (e.g., keyboard). In developing these interfaces, many design choices have a significant impact on the performance of the system. The objective of this study was to explore the design choices of a continuously-moving cursor neural prosthesis and optimize the interface to maximize information theoretic performance. We swept interface parameters of two keyboard-like tasks to find task and subject specific optimal parameters as measured by achieved bitrate using two rhesus macaques implanted with multielectrode arrays. In this report, we present the highest performing free-paced neural prosthesis under any recording modality with sustainable communication rates of up to 3.5 bits per second (bps). These findings demonstrate that meaningful high performance can be achieved using an intracortical neural prosthesis, and that, when optimized, these systems may be appropriate for use as communication devices for those with physical disabilities. PMID:25203982
Petrović, Jelena; Ibrić, Svetlana; Betz, Gabriele; Đurić, Zorica
2012-05-30
The main objective of the study was to develop artificial intelligence methods for optimization of drug release from matrix tablets regardless of the matrix type. Static and dynamic artificial neural networks of the same topology were developed to model dissolution profiles of different matrix tablets types (hydrophilic/lipid) using formulation composition, compression force used for tableting and tablets porosity and tensile strength as input data. Potential application of decision trees in discovering knowledge from experimental data was also investigated. Polyethylene oxide polymer and glyceryl palmitostearate were used as matrix forming materials for hydrophilic and lipid matrix tablets, respectively whereas selected model drugs were diclofenac sodium and caffeine. Matrix tablets were prepared by direct compression method and tested for in vitro dissolution profiles. Optimization of static and dynamic neural networks used for modeling of drug release was performed using Monte Carlo simulations or genetic algorithms optimizer. Decision trees were constructed following discretization of data. Calculated difference (f(1)) and similarity (f(2)) factors for predicted and experimentally obtained dissolution profiles of test matrix tablets formulations indicate that Elman dynamic neural networks as well as decision trees are capable of accurate predictions of both hydrophilic and lipid matrix tablets dissolution profiles. Elman neural networks were compared to most frequently used static network, Multi-layered perceptron, and superiority of Elman networks have been demonstrated. Developed methods allow simple, yet very precise way of drug release predictions for both hydrophilic and lipid matrix tablets having controlled drug release. Copyright © 2012 Elsevier B.V. All rights reserved.
Power prediction in mobile communication systems using an optimal neural-network structure.
Gao, X M; Gao, X Z; Tanskanen, J A; Ovaska, S J
1997-01-01
Presents a novel neural-network-based predictor for received power level prediction in direct sequence code division multiple access (DS/CDMA) systems. The predictor consists of an adaptive linear element (Adaline) followed by a multilayer perceptron (MLP). An important but difficult problem in designing such a cascade predictor is to determine the complexity of the networks. We solve this problem by using the predictive minimum description length (PMDL) principle to select the optimal numbers of input and hidden nodes. This approach results in a predictor with both good noise attenuation and excellent generalization capability. The optimized neural networks are used for predictive filtering of very noisy Rayleigh fading signals with 1.8 GHz carrier frequency. Our results show that the optimal neural predictor can provide smoothed in-phase and quadrature signals with signal-to-noise ratio (SNR) gains of about 12 and 7 dB at the urban mobile speeds of 5 and 50 km/h, respectively. The corresponding power signal SNR gains are about 11 and 5 dB. Therefore, the neural predictor is well suitable for power control applications where ldquodelaylessrdquo noise attenuation and efficient reduction of fast fading are required.
A stimulus-dependent spike threshold is an optimal neural coder.
Jones, Douglas L; Johnson, Erik C; Ratnam, Rama
2015-01-01
A neural code based on sequences of spikes can consume a significant portion of the brain's energy budget. Thus, energy considerations would dictate that spiking activity be kept as low as possible. However, a high spike-rate improves the coding and representation of signals in spike trains, particularly in sensory systems. These are competing demands, and selective pressure has presumably worked to optimize coding by apportioning a minimum number of spikes so as to maximize coding fidelity. The mechanisms by which a neuron generates spikes while maintaining a fidelity criterion are not known. Here, we show that a signal-dependent neural threshold, similar to a dynamic or adapting threshold, optimizes the trade-off between spike generation (encoding) and fidelity (decoding). The threshold mimics a post-synaptic membrane (a low-pass filter) and serves as an internal decoder. Further, it sets the average firing rate (the energy constraint). The decoding process provides an internal copy of the coding error to the spike-generator which emits a spike when the error equals or exceeds a spike threshold. When optimized, the trade-off leads to a deterministic spike firing-rule that generates optimally timed spikes so as to maximize fidelity. The optimal coder is derived in closed-form in the limit of high spike-rates, when the signal can be approximated as a piece-wise constant signal. The predicted spike-times are close to those obtained experimentally in the primary electrosensory afferent neurons of weakly electric fish (Apteronotus leptorhynchus) and pyramidal neurons from the somatosensory cortex of the rat. We suggest that KCNQ/Kv7 channels (underlying the M-current) are good candidates for the decoder. They are widely coupled to metabolic processes and do not inactivate. We conclude that the neural threshold is optimized to generate an energy-efficient and high-fidelity neural code.
A stimulus-dependent spike threshold is an optimal neural coder
Jones, Douglas L.; Johnson, Erik C.; Ratnam, Rama
2015-01-01
A neural code based on sequences of spikes can consume a significant portion of the brain's energy budget. Thus, energy considerations would dictate that spiking activity be kept as low as possible. However, a high spike-rate improves the coding and representation of signals in spike trains, particularly in sensory systems. These are competing demands, and selective pressure has presumably worked to optimize coding by apportioning a minimum number of spikes so as to maximize coding fidelity. The mechanisms by which a neuron generates spikes while maintaining a fidelity criterion are not known. Here, we show that a signal-dependent neural threshold, similar to a dynamic or adapting threshold, optimizes the trade-off between spike generation (encoding) and fidelity (decoding). The threshold mimics a post-synaptic membrane (a low-pass filter) and serves as an internal decoder. Further, it sets the average firing rate (the energy constraint). The decoding process provides an internal copy of the coding error to the spike-generator which emits a spike when the error equals or exceeds a spike threshold. When optimized, the trade-off leads to a deterministic spike firing-rule that generates optimally timed spikes so as to maximize fidelity. The optimal coder is derived in closed-form in the limit of high spike-rates, when the signal can be approximated as a piece-wise constant signal. The predicted spike-times are close to those obtained experimentally in the primary electrosensory afferent neurons of weakly electric fish (Apteronotus leptorhynchus) and pyramidal neurons from the somatosensory cortex of the rat. We suggest that KCNQ/Kv7 channels (underlying the M-current) are good candidates for the decoder. They are widely coupled to metabolic processes and do not inactivate. We conclude that the neural threshold is optimized to generate an energy-efficient and high-fidelity neural code. PMID:26082710
NASA Technical Reports Server (NTRS)
Decker, Arthur J. (Inventor)
2006-01-01
An artificial neural network is disclosed that processes holography generated characteristic pattern of vibrating structures along with finite-element models. The present invention provides for a folding operation for conditioning training sets for optimally training forward-neural networks to process characteristic fringe pattern. The folding pattern increases the sensitivity of the feed-forward network for detecting changes in the characteristic pattern The folding routine manipulates input pixels so as to be scaled according to the location in an intensity range rather than the position in the characteristic pattern.
Prabhu, Ashish A; Jayadeep, A
2017-04-21
The current study is focused on optimizing the parameters involved in enzymatic processing of red rice bran for maximizing total polyphenol (TP) and free radical scavenging activity (FRSA). The sequential optimization strategies using central composite design (CCD) and artificial neural network (ANN) modeling linked with genetic algorithm (GA) was performed to study the effect of incubation time (60-90 min), xylanase concentration (5-10 mg/g), cellulase concentration (5-10 mg/g) on the response, i.e., total polyphenol and FRSA. The result showed that incubation time has a negative effect on the response, while the square effect of xylanase and cellulase showed positive effect on the response. A maximum TP of 2,761 mg ferulic acid Eq/100 g bran and FRSA of 778.4 mg Catechin Eq/100 g bran was achieved with incubation time (min) = 60.491; xylanase (mg/g) = 5.4633; cellulase (mg/g) = 11.5825. Furthermore, ANN-GA-based optimization showed better predicting capabilities as compared to CCD.
Fast Simulation and Optimization Tool to Explore Selective Neural Stimulation
Dali, Mélissa; Rossel, Olivier; Guiraud, David
2016-01-01
In functional electrical stimulation, selective stimulation of axons is desirable to activate a specific target, in particular muscular function. This implies to simulate a fascicule without activating neighboring ones i.e. to be spatially selective. Spatial selectivity is achieved by the use of multicontact cuff electrodes over which the stimulation current is distributed. Because of the large number of parameters involved, numerical simulations provide a way to find and optimize electrode configuration. The present work offers a computation effective scheme and associated tool chain capable of simulating electrode-nerve interface and find the best spread of current to achieve spatial selectivity. PMID:27990231
Configuring artificial neural networks to implement function optimization
NASA Astrophysics Data System (ADS)
Sundaram, Ramakrishnan
2002-04-01
Threshold binary networks of the discrete Hopfield-type lead to the efficient retrieval of the regularized least-squares (LS) solution in certain inverse problem formulations. Partitions of these networks are identified based on forms of representation of the data. The objective criterion is optimized using sequential and parallel updates on these partitions. The algorithms consist of minimizing a suboptimal objective criterion in the currently active partition. Once the local minima is attained, an inactive partition is chosen to continue the minimization. This strategy is especially effective when substantial data must be processed by resources which are constrained either in space or available bandwidth.
Fast Simulation and Optimization Tool to Explore Selective Neural Stimulation.
Dali, Mélissa; Rossel, Olivier; Guiraud, David
2016-06-13
In functional electrical stimulation, selective stimulation of axons is desirable to activate a specific target, in particular muscular function. This implies to simulate a fascicule without activating neighboring ones i.e. to be spatially selective. Spatial selectivity is achieved by the use of multicontact cuff electrodes over which the stimulation current is distributed. Because of the large number of parameters involved, numerical simulations provide a way to find and optimize electrode configuration. The present work offers a computation effective scheme and associated tool chain capable of simulating electrode-nerve interface and find the best spread of current to achieve spatial selectivity.
Optimized Energy Transfer from Electron-hole pairs to Eu ions in GaN
NASA Astrophysics Data System (ADS)
Wei, Ruoqiao; Hernandez, Natalie; Mitchell, Brandon; Fujiwara, Yasufumi; Dierolf, Volkmar
Europium doped Gallium Nitride (GaN:Eu) has demonstrated potential for the red-emitting active layer in nitride-based light emitting diodes. Under above band gap excitation, the red emission was shown to increase due to the optimization of crystal growth conditions. This suggests that excitation efficiency had been improved, which would imply that the energy transfer from electron-hole pairs to Eu ions occurred on a faster time-scale. To test this assumption, we performed time-resolved spectroscopy measurements, under ps-scale time resolution, on samples with a variety of co-dopants and growth conditions. Results show that the energy is transferred on a time scale faster than ns and the excitation efficiency is influenced by the various growth parameters and co-dopants.
Tahriri, Farzad; Dawal, Siti Zawiah Md; Taha, Zahari
2014-01-01
A new multiobjective dynamic fuzzy genetic algorithm is applied to solve a fuzzy mixed-model assembly line sequencing problem in which the primary goals are to minimize the total make-span and minimize the setup number simultaneously. Trapezoidal fuzzy numbers are implemented for variables such as operation and travelling time in order to generate results with higher accuracy and representative of real-case data. An improved genetic algorithm called fuzzy adaptive genetic algorithm (FAGA) is proposed in order to solve this optimization model. In establishing the FAGA, five dynamic fuzzy parameter controllers are devised in which fuzzy expert experience controller (FEEC) is integrated with automatic learning dynamic fuzzy controller (ALDFC) technique. The enhanced algorithm dynamically adjusts the population size, number of generations, tournament candidate, crossover rate, and mutation rate compared with using fixed control parameters. The main idea is to improve the performance and effectiveness of existing GAs by dynamic adjustment and control of the five parameters. Verification and validation of the dynamic fuzzy GA are carried out by developing test-beds and testing using a multiobjective fuzzy mixed production assembly line sequencing optimization problem. The simulation results highlight that the performance and efficacy of the proposed novel optimization algorithm are more efficient than the performance of the standard genetic algorithm in mixed assembly line sequencing model. PMID:24982962
Tahriri, Farzad; Dawal, Siti Zawiah Md; Taha, Zahari
2014-01-01
A new multiobjective dynamic fuzzy genetic algorithm is applied to solve a fuzzy mixed-model assembly line sequencing problem in which the primary goals are to minimize the total make-span and minimize the setup number simultaneously. Trapezoidal fuzzy numbers are implemented for variables such as operation and travelling time in order to generate results with higher accuracy and representative of real-case data. An improved genetic algorithm called fuzzy adaptive genetic algorithm (FAGA) is proposed in order to solve this optimization model. In establishing the FAGA, five dynamic fuzzy parameter controllers are devised in which fuzzy expert experience controller (FEEC) is integrated with automatic learning dynamic fuzzy controller (ALDFC) technique. The enhanced algorithm dynamically adjusts the population size, number of generations, tournament candidate, crossover rate, and mutation rate compared with using fixed control parameters. The main idea is to improve the performance and effectiveness of existing GAs by dynamic adjustment and control of the five parameters. Verification and validation of the dynamic fuzzy GA are carried out by developing test-beds and testing using a multiobjective fuzzy mixed production assembly line sequencing optimization problem. The simulation results highlight that the performance and efficacy of the proposed novel optimization algorithm are more efficient than the performance of the standard genetic algorithm in mixed assembly line sequencing model.
NASA Astrophysics Data System (ADS)
Gao, Zhongmei; Shao, Xinyu; Jiang, Ping; Cao, Longchao; Zhou, Qi; Yue, Chen; Liu, Yang; Wang, Chunming
2016-09-01
It is of great significance to select appropriate welding process parameters for obtaining optimal weld geometry in hybrid laser-arc welding. An integrated optimization approach by combining Kriging model and GA is proposed to optimize process parameters. A four-factor, five-level experiment using Taguchi L25 is conducted considering laser power (P), welding current (A), distance between laser and arc (D) and traveling speed (V). Kriging model is adopted to approximate the relationship between process parameters and weld geometry, namely depth of penetration (DP), bead width (BW) and bead reinforcement (BR). The constructed Kriging model was used for parameters optimization by GA to maximize DP, minimize BW and ensure BR at a desired value. The effects of process parameters on weld geometry are analyzed. Microstructure and micro-hardness are also discussed. Verification experiments demonstrate that the obtained optimum values are in good agreement with experimental results.
Optimal Recognition Method of Human Activities Using Artificial Neural Networks
NASA Astrophysics Data System (ADS)
Oniga, Stefan; József, Sütő
2015-12-01
The aim of this research is an exhaustive analysis of the various factors that may influence the recognition rate of the human activity using wearable sensors data. We made a total of 1674 simulations on a publically released human activity database by a group of researcher from the University of California at Berkeley. In a previous research, we analyzed the influence of the number of sensors and their placement. In the present research we have examined the influence of the number of sensor nodes, the type of sensor node, preprocessing algorithms, type of classifier and its parameters. The final purpose is to find the optimal setup for best recognition rates with lowest hardware and software costs.
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.
Constant fan-in digital neural networks are VLSI-optimal
Beiu, V.
1995-12-31
The paper presents a theoretical proof revealing an intrinsic limitation of digital VLSI technology: its inability to cope with highly connected structures (e.g. neural networks). We are in fact able to prove that efficient digital VLSI implementations (known as VLSI-optimal when minimizing the AT{sup 2} complexity measure - A being the area of the chip, and T the delay for propagating the inputs to the outputs) of neural networks are achieved for small-constant fan-in gates. This result builds on quite recent ones dealing with a very close estimate of the area of neural networks when implemented by threshold gates, but it is also valid for classical Boolean gates. Limitations and open questions are presented in the conclusions.
NASA Astrophysics Data System (ADS)
Piotrowski, Adam P.; Napiorkowski, Jarosław J.
2011-09-01
SummaryAlthough neural networks have been widely applied to various hydrological problems, including river flow forecasting, for at least 15 years, they have usually been trained by means of gradient-based algorithms. Recently nature inspired Evolutionary Computation algorithms have rapidly developed as optimization methods able to cope not only with non-differentiable functions but also with a great number of local minima. Some of proposed Evolutionary Computation algorithms have been tested for neural networks training, but publications which compare their performance with gradient-based training methods are rare and present contradictory conclusions. The main goal of the present study is to verify the applicability of a number of recently developed Evolutionary Computation optimization methods, mostly from the Differential Evolution family, to multi-layer perceptron neural networks training for daily rainfall-runoff forecasting. In the present paper eight Evolutionary Computation methods, namely the first version of Differential Evolution (DE), Distributed DE with Explorative-Exploitative Population Families, Self-Adaptive DE, DE with Global and Local Neighbors, Grouping DE, JADE, Comprehensive Learning Particle Swarm Optimization and Efficient Population Utilization Strategy Particle Swarm Optimization are tested against the Levenberg-Marquardt algorithm - probably the most efficient in terms of speed and success rate among gradient-based methods. The Annapolis River catchment was selected as the area of this study due to its specific climatic conditions, characterized by significant seasonal changes in runoff, rapid floods, dry summers, severe winters with snowfall, snow melting, frequent freeze and thaw, and presence of river ice - conditions which make flow forecasting more troublesome. The overall performance of the Levenberg-Marquardt algorithm and the DE with Global and Local Neighbors method for neural networks training turns out to be superior to other
Cheng, Long; Hou, Zeng-Guang; Lin, Yingzi; Tan, Min; Zhang, Wenjun Chris; Wu, Fang-Xiang
2011-05-01
A recurrent neural network is proposed for solving the non-smooth convex optimization problem with the convex inequality and linear equality constraints. Since the objective function and inequality constraints may not be smooth, the Clarke's generalized gradients of the objective function and inequality constraints are employed to describe the dynamics of the proposed neural network. It is proved that the equilibrium point set of the proposed neural network is equivalent to the optimal solution of the original optimization problem by using the Lagrangian saddle-point theorem. Under weak conditions, the proposed neural network is proved to be stable, and the state of the neural network is convergent to one of its equilibrium points. Compared with the existing neural network models for non-smooth optimization problems, the proposed neural network can deal with a larger class of constraints and is not based on the penalty method. Finally, the proposed neural network is used to solve the identification problem of genetic regulatory networks, which can be transformed into a non-smooth convex optimization problem. The simulation results show the satisfactory identification accuracy, which demonstrates the effectiveness and efficiency of the proposed approach.
Single- and Multiple-Objective Optimization with Differential Evolution and Neural Networks
NASA Technical Reports Server (NTRS)
Rai, Man Mohan
2006-01-01
Genetic and evolutionary algorithms have been applied to solve numerous problems in engineering design where they have been used primarily as optimization procedures. These methods have an advantage over conventional gradient-based search procedures became they are capable of finding global optima of multi-modal functions and searching design spaces with disjoint feasible regions. They are also robust in the presence of noisy data. Another desirable feature of these methods is that they can efficiently use distributed and parallel computing resources since multiple function evaluations (flow simulations in aerodynamics design) can be performed simultaneously and independently on ultiple processors. For these reasons genetic and evolutionary algorithms are being used more frequently in design optimization. Examples include airfoil and wing design and compressor and turbine airfoil design. They are also finding increasing use in multiple-objective and multidisciplinary optimization. This lecture will focus on an evolutionary method that is a relatively new member to the general class of evolutionary methods called differential evolution (DE). This method is easy to use and program and it requires relatively few user-specified constants. These constants are easily determined for a wide class of problems. Fine-tuning the constants will off course yield the solution to the optimization problem at hand more rapidly. DE can be efficiently implemented on parallel computers and can be used for continuous, discrete and mixed discrete/continuous optimization problems. It does not require the objective function to be continuous and is noise tolerant. DE and applications to single and multiple-objective optimization will be included in the presentation and lecture notes. A method for aerodynamic design optimization that is based on neural networks will also be included as a part of this lecture. The method offers advantages over traditional optimization methods. It is more
NASA Technical Reports Server (NTRS)
Hovel, H. J.; Woodall, J. M.
1976-01-01
The three types of solar cells investigated were: (1) one consisting of a nGaAs substrate, a Zn doped pGaAs region, and a Zn doped Ga(1-x)Al(x)As layer, (2) one consisting of an nGaAs substrate, a Ge doped pGaAs region, and a pGa(1-x)Al(x)As upper layer, and (3) one consisting of an n+GaAs substrate, an nGa(1-x)Al(X)As region, a pGa(1-x)Bl(X) As region, and a pGa(1-y)Al(y)As upper layer. In all three cases, the upper alloy layer is thin and of high Al composition in order to obtain high spectral response over the widest possible range of photon energies. Spectral response, capacitance-voltage, current-voltage, diffusion length, sunlight (or the equivalent)-efficiency, and efficiency-temperature measurements were made as a function of device parameters in order to analyze and optimize the solar cell behavior.
NASA Astrophysics Data System (ADS)
Mantarcı, Asim; Kundakçı, Mutlu
2017-04-01
One of important material of III-nitrides can be said to be GaN with direct-wide band gap ( 3.4 eV) and many industrial devices such as solar cell, LED has been based on GaN thin film. In this research, we elaborately investigated growth of GaN thin film on Si(100) substrate by RF sputter technique and characterization of the film. We have successfully grown GaN thin film on Si substrate with hexagonal structure which has been confirmed by analysis of X-ray measurements. Also, we obtained structural properties of GaN film by (XRD) X-ray Diffraction measurements depending on different Argon, nitrogen and RF power values. During experiment, the value from 25sccm to 100sccm Argon gas value, the value from 0sccm to 4sccm Nitrogen gas value and from 50 watt to 125 watt RF power value has been applied. Among these values, we determined the best film in terms of crystalline structure of film. From AFM results, we attained and analyzed average roughness (Ra), maximum peak height (Rp), and maximum depth (Rv), average absolute slope of the profile (Δa)(°) of the fılms successfully. The film having the lowest roughness (Ra) has been achieved depending on different Argon, nitrogen and RF power values. Atomic Force Microscopy results confirmed that some of the films have homogeneous and uniform structure without any holes and crack; but others has voids referring impurities coming from growth process. To sum up, not only growing GaN thin film on Si substrate has been investigated, but also some of structural and morphological parameters' optimization has been studied, analyzed and the best film was determined in view of varied Argon, nitrogen and RF power values. For future direction, optimization of GaN thin film in detail can enable us to fabricate high quality film; therefore it will helps to improving device technology.
Lin, C.H.; Lo, Y.H. )
1993-03-01
The effects of strain and number of quantum wells on optical gain, differential gain, and nonlinear gain coefficient in 1.55 [mu]m InGaAs/InGaAsP strained-quantum-well lasers are theoretically investigated first. Well approximated empirical expressions are then proposed to model these effects. Using these formulas, one can easily and accurately predict the performance of a laser diode for a given structure. Therefore, these empirical formulas are useful tools for design and optimization of strained quantum well lasers. As a general design guideline revealed from the empirical formulas, the threshold current is reduced with the compressive strain, and the modulation band-width is most efficiently increased with the number of wells.
Automatic Optimization of the Computation Graph in the Nengo Neural Network Simulator.
Gosmann, Jan; Eliasmith, Chris
2017-01-01
One critical factor limiting the size of neural cognitive models is the time required to simulate such models. To reduce simulation time, specialized hardware is often used. However, such hardware can be costly, not readily available, or require specialized software implementations that are difficult to maintain. Here, we present an algorithm that optimizes the computational graph of the Nengo neural network simulator, allowing simulations to run more quickly on commodity hardware. This is achieved by merging identical operations into single operations and restructuring the accessed data in larger blocks of sequential memory. In this way, a time speed-up of up to 6.8 is obtained. While this does not beat the specialized OpenCL implementation of Nengo, this optimization is available on any platform that can run Python. In contrast, the OpenCL implementation supports fewer platforms and can be difficult to install.
Pirrung, Silvia M; van der Wielen, Luuk A M; van Beckhoven, Ruud F W C; van de Sandt, Emile J A X; Eppink, Michel H M; Ottens, Marcel
2017-01-05
Downstream process development is a major area of importance within the field of bioengineering. During the design of such a downstream process, important decisions have to be made regarding the type of unit operations as well as their sequence and their operating conditions. Current computational approaches addressing these issues either show a high level of simplification or struggle with computational speed. Therefore, this article presents a new approach that combines detailed mechanistic models and speed-enhancing artificial neural networks. This approach was able to simultaneously optimize a process with three different chromatographic columns toward yield with a minimum purity of 99.9%. The addition of artificial neural networks greatly accelerated this optimization. Due to high computational speed, the approach is easily extendable to include more unit operations. Therefore, it can be of great help in the acceleration of downstream process development. © 2017 American Institute of Chemical Engineers Biotechnol. Prog., 2017.
Automatic Optimization of the Computation Graph in the Nengo Neural Network Simulator
Gosmann, Jan; Eliasmith, Chris
2017-01-01
One critical factor limiting the size of neural cognitive models is the time required to simulate such models. To reduce simulation time, specialized hardware is often used. However, such hardware can be costly, not readily available, or require specialized software implementations that are difficult to maintain. Here, we present an algorithm that optimizes the computational graph of the Nengo neural network simulator, allowing simulations to run more quickly on commodity hardware. This is achieved by merging identical operations into single operations and restructuring the accessed data in larger blocks of sequential memory. In this way, a time speed-up of up to 6.8 is obtained. While this does not beat the specialized OpenCL implementation of Nengo, this optimization is available on any platform that can run Python. In contrast, the OpenCL implementation supports fewer platforms and can be difficult to install. PMID:28522970
Neural Network and Regression Methods Demonstrated in the Design Optimization of a Subsonic Aircraft
NASA Technical Reports Server (NTRS)
Hopkins, Dale A.; Lavelle, Thomas M.; Patnaik, Surya
2003-01-01
The neural network and regression methods of NASA Glenn Research Center s COMETBOARDS design optimization testbed were used to generate approximate analysis and design models for a subsonic aircraft operating at Mach 0.85 cruise speed. The analytical model is defined by nine design variables: wing aspect ratio, engine thrust, wing area, sweep angle, chord-thickness ratio, turbine temperature, pressure ratio, bypass ratio, fan pressure; and eight response parameters: weight, landing velocity, takeoff and landing field lengths, approach thrust, overall efficiency, and compressor pressure and temperature. The variables were adjusted to optimally balance the engines to the airframe. The solution strategy included a sensitivity model and the soft analysis model. Researchers generated the sensitivity model by training the approximators to predict an optimum design. The trained neural network predicted all response variables, within 5-percent error. This was reduced to 1 percent by the regression method. The soft analysis model was developed to replace aircraft analysis as the reanalyzer in design optimization. Soft models have been generated for a neural network method, a regression method, and a hybrid method obtained by combining the approximators. The performance of the models is graphed for aircraft weight versus thrust as well as for wing area and turbine temperature. The regression method followed the analytical solution with little error. The neural network exhibited 5-percent maximum error over all parameters. Performance of the hybrid method was intermediate in comparison to the individual approximators. Error in the response variable is smaller than that shown in the figure because of a distortion scale factor. The overall performance of the approximators was considered to be satisfactory because aircraft analysis with NASA Langley Research Center s FLOPS (Flight Optimization System) code is a synthesis of diverse disciplines: weight estimation, aerodynamic
Chang, P.S.; Poston, J.M.; Schroech, K.A.; Hou, H.S.
1995-12-31
Boiler performance optimization includes the preservation of efficiency, emission, capacity, and reliability. Competitive pressures require cost reduction and environmental compliance. It is a challenge for utility personnel to balance these requirements often demand tradeoffs. The Clean Air Act Amendment requires utilities to reduce NOx emission. NOx emission reduction has often been accomplished by installation of new low NOx burners. Boiler tuning for NOx control can be used as an alternative to low NOx burner installation. Specifically in tangentially-fired boilers, boiler tuning can be very effective in NOx reduction. A PC-based computer software program was developed to assist the tuning process. This software, System Optimization Analysis Program (SOAP), is a neural network based code which uses the self-adaptation learning process, with an adaptive filter added for data noise control. SOAP can use historical data as the knowledge base and provides a fast optimal solution to adaptive control problems. SOAP was tested at TVA`s Kingston Unit 3 tangentially coal-fired furnace for NOx reduction. With a well-organized test plan, the optimized solution was reached with 16 tests at each test series load level. SOAP will be used for other plant equipment or system optimization, such as pulverizer performance, combustion system optimization, compared thermal performance design, and boiler tube leak detection and allocation.
Optimal reentry prediction of space objects from LEO using RSM and GA
NASA Astrophysics Data System (ADS)
Mutyalarao, M.; Raj, M. Xavier James
2012-07-01
The accurate estimation of the orbital life time (OLT) of decaying near-Earth objects is of considerable importance for the prediction of risk object re-entry time and hazard assessment as well as for mitigation strategies. Recently, due to the reentries of large number of risk objects, which poses threat to the human life and property, a great concern is developed in the space scientific community all over the World. The evolution of objects in Low Earth Orbit (LEO) is determined by a complex interplay of the perturbing forces, mainly due to atmospheric drag and Earth gravity. These orbits are mostly in low eccentric (eccentricity < 0.2) and have variations in perigee and apogee altitudes due to perturbations during a revolution. The changes in the perigee and apogee altitudes of these orbits are mainly due to the gravitational perturbations of the Earth and the atmospheric density. It has become necessary to use extremely complex force models to match with the present operational requirements and observational techniques. Further the re-entry time of the objects in such orbits is sensitive to the initial conditions. In this paper the problem of predicting re-entry time is attempted as an optimal estimation problem. It is known that the errors are more in eccentricity for the observations based on two line elements (TLEs). Thus two parameters, initial eccentricity and ballistic coefficient, are chosen for optimal estimation. These two parameters are computed with response surface method (RSM) using a genetic algorithm (GA) for the selected time zones, based on rough linear variation of response parameter, the mean semi-major axis during orbit evolution. Error minimization between the observed and predicted mean Semi-major axis is achieved by the application of an optimization algorithm such as Genetic Algorithm (GA). The basic feature of the present approach is that the model and measurement errors are accountable in terms of adjusting the ballistic coefficient
DC- and IF-noise performance optimization of GaAs Schottky diodes for THz applications
NASA Astrophysics Data System (ADS)
Cojocari, O.; Biber, S.; Mottet, B.; Rodriguez-Girones, M.; Hartnagel, H. L.; Schmidt, L.-P.
2005-01-01
This paper presents results which originated from a long-term systematic optimization of surface processing prior to anode formation of THz Schottky-based components. Particularly, four most promising surface-processing approaches are carefully investigated separately and in combination in order to understand the chemical and physical processes occurring on a GaAs surface. A reliable technological approach for anode formation is identified, which exhibits optimal diode characteristics and production repeatability. A model is proposed for the influence of each process on the subsequent one in the fabrication process sequence. DC- and IF-noise measurements are performed using an automated measurement system providing statistically significant data. Very good dc-parameters such as a series resistance of Rs = 15 Ω, an ideality factor N = 1.168, a reverse current Is = 0.024 fA and an IF-noise temperature of 257 K at 1 mA current bias with a good uniformity are achieved for non-cooled Schottky diodes with an anode diameter of 1 µm. The best noise figure is measured to be as low as 220 K at 3.8 GHz and 1 mA current bias.
NASA Astrophysics Data System (ADS)
Zhang, Enlai; Hou, Liang; Shen, Chao; Shi, Yingliang; Zhang, Yaxiang
2016-01-01
To better solve the complex non-linear problem between the subjective sound quality evaluation results and objective psychoacoustics parameters, a method for the prediction of the sound quality is put forward by using a back propagation neural network (BPNN) based on particle swarm optimization (PSO), which is optimizing the initial weights and thresholds of BP network neurons through the PSO. In order to verify the effectiveness and accuracy of this approach, the noise signals of the B-Class vehicles from the idle speed to 120 km h-1 measured by the artificial head, are taken as a target. In addition, this paper describes a subjective evaluation experiment on the sound quality annoyance inside the vehicles through a grade evaluation method, by which the annoyance of each sample is obtained. With the use of Artemis software, the main objective psychoacoustic parameters of each noise sample are calculated. These parameters include loudness, sharpness, roughness, fluctuation, tonality, articulation index (AI) and A-weighted sound pressure level. Furthermore, three evaluation models with the same artificial neural network (ANN) structure are built: the standard BPNN model, the genetic algorithm-back-propagation neural network (GA-BPNN) model and the PSO-back-propagation neural network (PSO-BPNN) model. After the network training and the evaluation prediction on the three models’ network based on experimental data, it proves that the PSO-BPNN method can achieve convergence more quickly and improve the prediction accuracy of sound quality, which can further lay a foundation for the control of the sound quality inside vehicles.
NASA Astrophysics Data System (ADS)
Hasegawa, Mikio; Tran, Ha Nguyen; Miyamoto, Goh; Murata, Yoshitoshi; Harada, Hiroshi; Kato, Shuzo
We propose a neurodynamical approach to a large-scale optimization problem in Cognitive Wireless Clouds, in which a huge number of mobile terminals with multiple different air interfaces autonomously utilize the most appropriate infrastructure wireless networks, by sensing available wireless networks, selecting the most appropriate one, and reconfiguring themselves with seamless handover to the target networks. To deal with such a cognitive radio network, game theory has been applied in order to analyze the stability of the dynamical systems consisting of the mobile terminals' distributed behaviors, but it is not a tool for globally optimizing the state of the network. As a natural optimization dynamical system model suitable for large-scale complex systems, we introduce the neural network dynamics which converges to an optimal state since its property is to continually decrease its energy function. In this paper, we apply such neurodynamics to the optimization problem of radio access technology selection. We compose a neural network that solves the problem, and we show that it is possible to improve total average throughput simply by using distributed and autonomous neuron updates on the terminal side.
NASA Technical Reports Server (NTRS)
Patnaik, Surya N.; Guptill, James D.; Hopkins, Dale A.; Lavelle, Thomas M.
2000-01-01
The NASA Engine Performance Program (NEPP) can configure and analyze almost any type of gas turbine engine that can be generated through the interconnection of a set of standard physical components. In addition, the code can optimize engine performance by changing adjustable variables under a set of constraints. However, for engine cycle problems at certain operating points, the NEPP code can encounter difficulties: nonconvergence in the currently implemented Powell's optimization algorithm and deficiencies in the Newton-Raphson solver during engine balancing. A project was undertaken to correct these deficiencies. Nonconvergence was avoided through a cascade optimization strategy, and deficiencies associated with engine balancing were eliminated through neural network and linear regression methods. An approximation-interspersed cascade strategy was used to optimize the engine's operation over its flight envelope. Replacement of Powell's algorithm by the cascade strategy improved the optimization segment of the NEPP code. The performance of the linear regression and neural network methods as alternative engine analyzers was found to be satisfactory. This report considers two examples-a supersonic mixed-flow turbofan engine and a subsonic waverotor-topped engine-to illustrate the results, and it discusses insights gained from the improved version of the NEPP code.
NASA Astrophysics Data System (ADS)
Chtioui, Younes; Panigrahi, Suranjan; Marsh, Ronald A.
1998-11-01
The probabilistic neural network (PNN) is based on the estimation of the probability density functions. The estimation of these density functions uses smoothing parameters that represent the width of the activation functions. A two-step numerical procedure is developed for the optimization of the smoothing parameters of the PNN: a rough optimization by the conjugate gradient method and a fine optimization by the approximate Newton method. The thrust is to compare the classification performances of the improved PNN and the standard back-propagation neural network (BPNN). Comparisons are performed on a food quality problem: french fry classification into three different color classes (light, normal, and dark). The optimized PNN correctly classifies 96.19% of the test data, whereas the BPNN classifies only 93.27% of the same data. Moreover, the PNN is more stable than the BPNN with regard to the random initialization. The optimized PNN requires 1464 s for training compared to only 71 s required by the BPNN.
Jacob, Samuel; Banerjee, Rintu
2016-08-01
A novel approach to overcome the acidification problem has been attempted in the present study by codigesting industrial potato waste (PW) with Pistia stratiotes (PS, an aquatic weed). The effectiveness of codigestion of the weed and PW was tested in an equal (1:1) proportion by weight with substrate concentration of 5g total solid (TS)/L (2.5gPW+2.5gPS) which resulted in enhancement of methane yield by 76.45% as compared to monodigestion of PW with a positive synergistic effect. Optimization of process parameters was conducted using central composite design (CCD) based response surface methodology (RSM) and artificial neural network (ANN) coupled genetic algorithm (GA) model. Upon comparison of these two optimization techniques, ANN-GA model obtained through feed forward back propagation methodology was found to be efficient and yielded 447.4±21.43LCH4/kgVSfed (0.279gCH4/kgCODvs) which is 6% higher as compared to the CCD-RSM based approach. Copyright © 2016 Elsevier Ltd. All rights reserved.
Neural network cascade optimizes microRNA biomarker selection for nasopharyngeal cancer prognosis.
Zhu, Wenliang; Kan, Xuan
2014-01-01
MicroRNAs (miRNAs) have been shown to be promising biomarkers in predicting cancer prognosis. However, inappropriate or poorly optimized processing and modeling of miRNA expression data can negatively affect prediction performance. Here, we propose a holistic solution for miRNA biomarker selection and prediction model building. This work introduces the use of a neural network cascade, a cascaded constitution of small artificial neural network units, for evaluating miRNA expression and patient outcome. A miRNA microarray dataset of nasopharyngeal carcinoma was retrieved from Gene Expression Omnibus to illustrate the methodology. Results indicated a nonlinear relationship between miRNA expression and patient death risk, implying that direct comparison of expression values is inappropriate. However, this method performs transformation of miRNA expression values into a miRNA score, which linearly measures death risk. Spearman correlation was calculated between miRNA scores and survival status for each miRNA. Finally, a nine-miRNA signature was optimized to predict death risk after nasopharyngeal carcinoma by establishing a neural network cascade consisting of 13 artificial neural network units. Area under the ROC was 0.951 for the internal validation set and had a prediction accuracy of 83% for the external validation set. In particular, the established neural network cascade was found to have strong immunity against noise interference that disturbs miRNA expression values. This study provides an efficient and easy-to-use method that aims to maximize clinical application of miRNAs in prognostic risk assessment of patients with cancer.
Neural Network and Response Surface Methodology for Rocket Engine Component Optimization
NASA Technical Reports Server (NTRS)
Vaidyanathan, Rajkumar; Papita, Nilay; Shyy, Wei; Tucker, P. Kevin; Griffin, Lisa W.; Haftka, Raphael; Fitz-Coy, Norman; McConnaughey, Helen (Technical Monitor)
2000-01-01
The goal of this work is to compare the performance of response surface methodology (RSM) and two types of neural networks (NN) to aid preliminary design of two rocket engine components. A data set of 45 training points and 20 test points obtained from a semi-empirical model based on three design variables is used for a shear coaxial injector element. Data for supersonic turbine design is based on six design variables, 76 training, data and 18 test data obtained from simplified aerodynamic analysis. Several RS and NN are first constructed using the training data. The test data are then employed to select the best RS or NN. Quadratic and cubic response surfaces. radial basis neural network (RBNN) and back-propagation neural network (BPNN) are compared. Two-layered RBNN are generated using two different training algorithms, namely solverbe and solverb. A two layered BPNN is generated with Tan-Sigmoid transfer function. Various issues related to the training of the neural networks are addressed including number of neurons, error goals, spread constants and the accuracy of different models in representing the design space. A search for the optimum design is carried out using a standard gradient-based optimization algorithm over the response surfaces represented by the polynomials and trained neural networks. Usually a cubic polynominal performs better than the quadratic polynomial but exceptions have been noticed. Among the NN choices, the RBNN designed using solverb yields more consistent performance for both engine components considered. The training of RBNN is easier as it requires linear regression. This coupled with the consistency in performance promise the possibility of it being used as an optimization strategy for engineering design problems.
Shape Optimization of Supersonic Turbines Using Response Surface and Neural Network Methods
NASA Technical Reports Server (NTRS)
Papila, Nilay; Shyy, Wei; Griffin, Lisa W.; Dorney, Daniel J.
2001-01-01
Turbine performance directly affects engine specific impulse, thrust-to-weight ratio, and cost in a rocket propulsion system. A global optimization framework combining the radial basis neural network (RBNN) and the polynomial-based response surface method (RSM) is constructed for shape optimization of a supersonic turbine. Based on the optimized preliminary design, shape optimization is performed for the first vane and blade of a 2-stage supersonic turbine, involving O(10) design variables. The design of experiment approach is adopted to reduce the data size needed by the optimization task. It is demonstrated that a major merit of the global optimization approach is that it enables one to adaptively revise the design space to perform multiple optimization cycles. This benefit is realized when an optimal design approaches the boundary of a pre-defined design space. Furthermore, by inspecting the influence of each design variable, one can also gain insight into the existence of multiple design choices and select the optimum design based on other factors such as stress and materials considerations.
NASA Astrophysics Data System (ADS)
Greenlee, Jordan D.; Feigelson, Boris N.; Anderson, Travis J.; Tadjer, Marko J.; Hite, Jennifer K.; Mastro, Michael A.; Eddy, Charles R.; Hobart, Karl D.; Kub, Francis J.
2014-08-01
The first step of a multi-cycle rapid thermal annealing process was systematically studied. The surface, structure, and optical properties of Mg implanted GaN thin films annealed at temperatures ranging from 900 to 1200 °C were investigated by Raman spectroscopy, photoluminescence, UV-visible spectroscopy, atomic force microscopy, and Nomarski microscopy. The GaN thin films are capped with two layers of in-situ metal organic chemical vapor deposition -grown AlN and annealed in 24 bar of N2 overpressure to avoid GaN decomposition. The crystal quality of the GaN improves with increasing annealing temperature as confirmed by UV-visible spectroscopy and the full widths at half maximums of the E2 and A1 (LO) Raman modes. The crystal quality of films annealed above 1100 °C exceeds the quality of the as-grown films. At 1200 °C, Mg is optically activated, which is determined by photoluminescence measurements. However, at 1200 °C, the GaN begins to decompose as evidenced by pit formation on the surface of the samples. Therefore, it was determined that the optimal temperature for the first step in a multi-cycle rapid thermal anneal process should be conducted at 1150 °C due to crystal quality and surface morphology considerations.
Greenlee, Jordan D.; Feigelson, Boris N.; Anderson, Travis J.; Hite, Jennifer K.; Mastro, Michael A.; Eddy, Charles R.; Hobart, Karl D.; Kub, Francis J.; Tadjer, Marko J.
2014-08-14
The first step of a multi-cycle rapid thermal annealing process was systematically studied. The surface, structure, and optical properties of Mg implanted GaN thin films annealed at temperatures ranging from 900 to 1200 °C were investigated by Raman spectroscopy, photoluminescence, UV-visible spectroscopy, atomic force microscopy, and Nomarski microscopy. The GaN thin films are capped with two layers of in-situ metal organic chemical vapor deposition -grown AlN and annealed in 24 bar of N{sub 2} overpressure to avoid GaN decomposition. The crystal quality of the GaN improves with increasing annealing temperature as confirmed by UV-visible spectroscopy and the full widths at half maximums of the E{sub 2} and A{sub 1} (LO) Raman modes. The crystal quality of films annealed above 1100 °C exceeds the quality of the as-grown films. At 1200 °C, Mg is optically activated, which is determined by photoluminescence measurements. However, at 1200 °C, the GaN begins to decompose as evidenced by pit formation on the surface of the samples. Therefore, it was determined that the optimal temperature for the first step in a multi-cycle rapid thermal anneal process should be conducted at 1150 °C due to crystal quality and surface morphology considerations.
Aminiazar, Wahab; Najafi, Farid; Nekoui, Mohammad Ali
2013-08-14
There is an increasing trend in using robots for medical purposes. One specific area is rehabilitation. Rehabilitation is one of the non-drug treatments in community health which means the restoration of the abilities to maximize independence. It is a prolonged work and costly labor. On the other hand, by using the flexible and efficient robots in rehabilitation area, this process will be more useful for handicapped patients. In this study, a rule-based intelligent control methodology is proposed to mimic the behavior of a healthy limb in a satisfactory way by a 2-DOF planar robot. Inverse kinematic of the planar robot will be solved by neural networks and control parameters will be optimized by genetic algorithm, as rehabilitation progress. The results of simulations are presented by defining a physiotherapy simple mode on desired trajectory. MATLAB/Simulink is used for simulations. The system is capable of learning the action of the physiotherapist for each patient and imitating this behaviour in the absence of a physiotherapist that can be called robotherapy. In this study, a therapeutic exercise planar 2-DOF robot is designed and controlled for lower-limb rehabilitation. The robot manipulator is controlled by combination of hybrid and adaptive controls. Some safety factors and stability constraints are defined and obtained. The robot is stopped when the safety factors are not satisfied. Kinematics of robot is estimated by an MLP neural network and proper control parameters are achieved using GA optimization.
2013-01-01
Background There is an increasing trend in using robots for medical purposes. One specific area is rehabilitation. Rehabilitation is one of the non-drug treatments in community health which means the restoration of the abilities to maximize independence. It is a prolonged work and costly labor. On the other hand, by using the flexible and efficient robots in rehabilitation area, this process will be more useful for handicapped patients. Methods In this study, a rule-based intelligent control methodology is proposed to mimic the behavior of a healthy limb in a satisfactory way by a 2-DOF planar robot. Inverse kinematic of the planar robot will be solved by neural networks and control parameters will be optimized by genetic algorithm, as rehabilitation progress. Results The results of simulations are presented by defining a physiotherapy simple mode on desired trajectory. MATLAB/Simulink is used for simulations. The system is capable of learning the action of the physiotherapist for each patient and imitating this behaviour in the absence of a physiotherapist that can be called robotherapy. Conclusions In this study, a therapeutic exercise planar 2-DOF robot is designed and controlled for lower-limb rehabilitation. The robot manipulator is controlled by combination of hybrid and adaptive controls. Some safety factors and stability constraints are defined and obtained. The robot is stopped when the safety factors are not satisfied. Kinematics of robot is estimated by an MLP neural network and proper control parameters are achieved using GA optimization. PMID:23945420
Optimization of magneto-optical spatial light modulators for neural networks
NASA Astrophysics Data System (ADS)
Chani, V. I.; Chervonenkis, Andrey Y.; Kirykhin, Nikolay N.
1990-08-01
The performance of neural networks with Ceedback is determined by electrically addressable magneto-optical (MO) spatial light . modula-'' tors (5LM). It was shown that MO SLM may be used. in neural networks but it''s necessary to modificate traditional MO SLM in order to achi eve high switching rate. In this work we present the xnod. ificated MO SLM structure MO media''s physical properties optimized. for achieving high rate switching the MO SLM operational margin and the way$ of its widening. 1 . T- TION An important role in artificial neural networks belongs to electrically addressible programmable SLM. They are particu]ry important if feedback is considered in neural network architecture''. The major requirements to SLIvI''s are high rate switching time providing effecti ye itteration process and high reliability. Among known up to date types of SLM (liquid crystalline RZLT ceramics etc) most attractive are recently developed MO SLM based on epitaxial films of Bisubsti tut?d iron garnet (BiRIG). Two variants of MOSLM''s are conimercially produced on of which (LISA ELSP etc) is oriented for nonmechanicalprinters while the other (SIGHT MOD Semetex) is developed mainly for plane display sys tems. Some of above mentioned MOSLM types have sufficient high rate switching time (typical frame rate for 128x128 SIGHT MOD is 20 ms). In SIGHT MOD variant with 128x128 array where nominal line resistance is in the range of 40-60 Ohm thermal limitation determine
NASA Technical Reports Server (NTRS)
Hopkins, Dale A.; Patnaik, Surya N.
2000-01-01
A preliminary aircraft engine design methodology is being developed that utilizes a cascade optimization strategy together with neural network and regression approximation methods. The cascade strategy employs different optimization algorithms in a specified sequence. The neural network and regression methods are used to approximate solutions obtained from the NASA Engine Performance Program (NEPP), which implements engine thermodynamic cycle and performance analysis models. The new methodology is proving to be more robust and computationally efficient than the conventional optimization approach of using a single optimization algorithm with direct reanalysis. The methodology has been demonstrated on a preliminary design problem for a novel subsonic turbofan engine concept that incorporates a wave rotor as a cycle-topping device. Computations of maximum thrust were obtained for a specific design point in the engine mission profile. The results (depicted in the figure) show a significant improvement in the maximum thrust obtained using the new methodology in comparison to benchmark solutions obtained using NEPP in a manual design mode.
Schliebs, Stefan; Defoin-Platel, Michaël; Worner, Sue; Kasabov, Nikola
2009-01-01
This study introduces a quantum-inspired spiking neural network (QiSNN) as an integrated connectionist system, in which the features and parameters of an evolving spiking neural network are optimized together with the use of a quantum-inspired evolutionary algorithm. We propose here a novel optimization method that uses different representations to explore the two search spaces: A binary representation for optimizing feature subsets and a continuous representation for evolving appropriate real-valued configurations of the spiking network. The properties and characteristics of the improved framework are studied on two different synthetic benchmark datasets. Results are compared to traditional methods, namely a multi-layer-perceptron and a naïve Bayesian classifier (NBC). A previously used real world ecological dataset on invasive species establishment prediction is revisited and new results are obtained and analyzed by an ecological expert. The proposed method results in a much faster convergence to an optimal solution (or a close to it), in a better accuracy, and in a more informative set of features selected.
NASA Astrophysics Data System (ADS)
Koyuncu, A.; Cigeroglu, E.; Özgüven, H. N.
2017-10-01
In this study, a new approach is proposed for identification of structural nonlinearities by employing cascaded optimization and neural networks. Linear finite element model of the system and frequency response functions measured at arbitrary locations of the system are used in this approach. Using the finite element model, a training data set is created, which appropriately spans the possible nonlinear configurations space of the system. A classification neural network trained on these data sets then localizes and determines the types of all nonlinearities associated with the nonlinear degrees of freedom in the system. A new training data set spanning the parametric space associated with the determined nonlinearities is created to facilitate parametric identification. Utilizing this data set, initially, a feed forward regression neural network is trained, which parametrically identifies the classified nonlinearities. Then, the results obtained are further improved by carrying out an optimization which uses network identified values as starting points. Unlike identification methods available in literature, the proposed approach does not require data collection from the degrees of freedoms where nonlinear elements are attached, and furthermore, it is sufficiently accurate even in the presence of measurement noise. The application of the proposed approach is demonstrated on an example system with nonlinear elements and on a real life experimental setup with a local nonlinearity.
Tao, Tao; Zhi, Ting; Liu, Bin; Li, Mingxue; Zhuang, Zhe; Dai, Jiangping; Li, Yi; Jiang, Fulong; Luo, Wenjun; Xie, Zili; Chen, Dunjun; Chen, Peng; Li, Zhaosheng; Zou, Zhigang; Zhang, Rong; Zheng, Youdou
2016-01-01
The photoelectrodes based on III-nitride semiconductors with high energy conversion efficiency especially for those self-driven ones are greatly desirable for hydrogen generation. In this study, highly ordered InGaN/GaN multiple-quantum-well nanorod-based photoelectrodes have been fabricated by a soft UV-curing nano-imprint lithography and a top-down etching technique, which improve the incident photon conversion efficiency (IPCE) from 16% (planar structure) to 42% (@ wavelength = 400 nm). More significantly, the turn-on voltage is reduced low to −0.6 V, which indicates the possibility of achieving self-driven. Furthermore, SiO2/Si3N4 dielectric distributed Bragg reflectors are employed to further improve the IPCE up to 60%. And the photocurrent (@ 1.1 V) is enhanced from 0.37 mA/cm2 (original planar structure) to 1.5 mA/cm2. These improvements may accelerate the possible applications for hydrogen generation with high energy-efficiency. PMID:26853933
Tao, Tao; Zhi, Ting; Liu, Bin; Li, Mingxue; Zhuang, Zhe; Dai, Jiangping; Li, Yi; Jiang, Fulong; Luo, Wenjun; Xie, Zili; Chen, Dunjun; Chen, Peng; Li, Zhaosheng; Zou, Zhigang; Zhang, Rong; Zheng, Youdou
2016-02-08
The photoelectrodes based on III-nitride semiconductors with high energy conversion efficiency especially for those self-driven ones are greatly desirable for hydrogen generation. In this study, highly ordered InGaN/GaN multiple-quantum-well nanorod-based photoelectrodes have been fabricated by a soft UV-curing nano-imprint lithography and a top-down etching technique, which improve the incident photon conversion efficiency (IPCE) from 16% (planar structure) to 42% (@ wavelength = 400 nm). More significantly, the turn-on voltage is reduced low to -0.6 V, which indicates the possibility of achieving self-driven. Furthermore, SiO2/Si3N4 dielectric distributed Bragg reflectors are employed to further improve the IPCE up to 60%. And the photocurrent (@ 1.1 V) is enhanced from 0.37 mA/cm(2) (original planar structure) to 1.5 mA/cm(2). These improvements may accelerate the possible applications for hydrogen generation with high energy-efficiency.
Xue, Y.; Liu, S.; Hu, Y.; Yang, J.; Chen, Q.
2007-01-01
To improve the accuracy in prediction, Genetic Algorithm based Adaptive Neural Network Ensemble (GA-ANNE) is presented. Intersections are allowed between different training sets based on the fuzzy clustering analysis, which ensures the diversity as well as the accuracy of individual Neural Networks (NNs). Moreover, to improve the accuracy of the adaptive weights of individual NNs, GA is used to optimize the cluster centers. Empirical results in predicting carbon flux of Duke Forest reveal that GA-ANNE can predict the carbon flux more accurately than Radial Basis Function Neural Network (RBFNN), Bagging NN ensemble, and ANNE. ?? 2007 IEEE.
Constructing Optimal Prediction Intervals by Using Neural Networks and Bootstrap Method.
Khosravi, Abbas; Nahavandi, Saeid; Srinivasan, Dipti; Khosravi, Rihanna
2015-08-01
This brief proposes an efficient technique for the construction of optimized prediction intervals (PIs) by using the bootstrap technique. The method employs an innovative PI-based cost function in the training of neural networks (NNs) used for estimation of the target variance in the bootstrap method. An optimization algorithm is developed for minimization of the cost function and adjustment of NN parameters. The performance of the optimized bootstrap method is examined for seven synthetic and real-world case studies. It is shown that application of the proposed method improves the quality of constructed PIs by more than 28% over the existing technique, leading to narrower PIs with a coverage probability greater than the nominal confidence level.
Kwok, T; Smith, K A
2000-09-01
The aim of this paper is to study both the theoretical and experimental properties of chaotic neural network (CNN) models for solving combinatorial optimization problems. Previously we have proposed a unifying framework which encompasses the three main model types, namely, Chen and Aihara's chaotic simulated annealing (CSA) with decaying self-coupling, Wang and Smith's CSA with decaying timestep, and the Hopfield network with chaotic noise. Each of these models can be represented as a special case under the framework for certain conditions. This paper combines the framework with experimental results to provide new insights into the effect of the chaotic neurodynamics of each model. By solving the N-queen problem of various sizes with computer simulations, the CNN models are compared in different parameter spaces, with optimization performance measured in terms of feasibility, efficiency, robustness and scalability. Furthermore, characteristic chaotic neurodynamics crucial to effective optimization are identified, together with a guide to choosing the corresponding model parameters.
Neural network-based optimal adaptive output feedback control of a helicopter UAV.
Nodland, David; Zargarzadeh, Hassan; Jagannathan, Sarangapani
2013-07-01
Helicopter unmanned aerial vehicles (UAVs) are widely used for both military and civilian operations. Because the helicopter UAVs are underactuated nonlinear mechanical systems, high-performance controller design for them presents a challenge. This paper introduces an optimal controller design via an output feedback for trajectory tracking of a helicopter UAV, using a neural network (NN). The output-feedback control system utilizes the backstepping methodology, employing kinematic and dynamic controllers and an NN observer. The online approximator-based dynamic controller learns the infinite-horizon Hamilton-Jacobi-Bellman equation in continuous time and calculates the corresponding optimal control input by minimizing a cost function, forward-in-time, without using the value and policy iterations. Optimal tracking is accomplished by using a single NN utilized for the cost function approximation. The overall closed-loop system stability is demonstrated using Lyapunov analysis. Finally, simulation results are provided to demonstrate the effectiveness of the proposed control design for trajectory tracking.
Design and optimization of very high power density monochromatic GaAs photovoltaic cells
Algora, C.; Diaz, V.
1998-09-01
This paper deals with the structure optimization of very high power density monochromatic GaAs photovoltaic cells and the theoretical prediction of their performance at irradiances ranging from 0.1 to 100 W/cm{sup 2}. A multifaceted optimum design including the front metal grid, device size and the semiconductor layer structure is presented. The variation in efficiency depending on emitter thickness, base thickness, emitter doping and base doping is also addressed. The objective of this being the configuration of a structure suitable for working up to 100 W/cm{sup 2} without the detrimental influence of series resistance. For this, a detailed analysis of the effect of series resistance and the quantitative determination of its different components is carried out. The optimum wavelength is 830 nm at 300 K for all the analyzed light intensities, in which a 63% peak efficiency under an irradiance of 100 W/cm{sup 2} for a p/n structure is obtained. The temperature effect on device performance in the 273--350 K range is also studied. Finally, the influence of device processing is analyzed.
Optimization of thermoelectric properties for rough nano-ridge GaAs/AlAs superlattice structure
NASA Astrophysics Data System (ADS)
Wu, Chao-Wei; Wu, Yuh-Renn
2016-11-01
In this paper, optimizations of thermoelectric(TE) properties for the rough surface of the nano-ridge GaAs/AlAs superlattice(SL) structure are investigated. The nano-ridge featured with rough surface at both sides of the SL structure is introduced, where the modification of the phonon spatial confinement and phonon surface roughness scattering are taken into account. The elastic continuum model is employed to calculate the phonon dispersion relation and the related phonon group velocity. Reported experimental results with SL structures were used for verification of our model. The lattice thermal conductivity, electrical conductivity, Seebeck coefficient, and electronic thermal conductivity are calculated by Boltzmann transport equations and relaxation time approximation. Simulation results show that the nano-ridge SL structure with certain periodicity and phonon surface roughness scattering have strong influences on the TE properties. Highest ZT in our calculation is 1.285 at 300K and the ZT value of 3.04 is obtained at 1000K.
Optimization of GaN MOVPE growth on patterned Si substrates using spectroscopic in situ reflectance
NASA Astrophysics Data System (ADS)
Strittmatter, A.; Reißmann, L.; Trepk, T.; Pohl, U. W.; Bimberg, D.; Zettler, J.-T.
2004-12-01
In real-time monitoring of III-Nitride growth on patterned and masked substrates by spectroscopic reflectance, a characteristic interference pattern generated by the superposition of wave-fronts reflected at different μm-sized structures at the sample surface is measured. Up to now this time- and wavelength-dependent pattern was used only for empirical fingerprint-evaluation of III-Nitride growth processes which employ patterning or masking for bulk defect reduction. In this paper, we report on the analysis of real-time spectroscopic reflectance data measured in the range 1.65-4.5 eV during the epitaxial growth of GaN layers on structured Si(1 1 1) substrates. The successful implementation of a two-dimensional interference model into conventional thin-film analysis algorithms enables the quantitative analysis of characteristic vertical and lateral growth rates and overgrowth mechanisms involved. The new method is applied to optimize III-Nitride growth processes on patterned silicon substrates used for subsequent III-Nitride device growth.
NASA Astrophysics Data System (ADS)
Dropka, Natasha; Holena, Martin
2017-08-01
In directional solidification of silicon, the solid-liquid interface shape plays a crucial role for the quality of crystals. The interface shape can be influenced by forced convection using travelling magnetic fields. Up to now, there is no general and explicit methodology to identify the relation and the optimum combination of magnetic and growth parameters e.g., frequency, phase shift, current magnitude and interface deflection in a buoyancy regime. In the present study, 2D CFD modeling was used to generate data for the design and training of artificial neural networks and for Gaussian process modeling. The aim was to quickly assess the complex nonlinear dependences among the parameters and to optimize them for the interface flattening. The first encouraging results are presented and the pros and cons of artificial neural networks and Gaussian process modeling discussed.
Elements of an algorithm for optimizing a parameter-structural neural network
NASA Astrophysics Data System (ADS)
Mrówczyńska, Maria
2016-06-01
The field of processing information provided by measurement results is one of the most important components of geodetic technologies. The dynamic development of this field improves classic algorithms for numerical calculations in the aspect of analytical solutions that are difficult to achieve. Algorithms based on artificial intelligence in the form of artificial neural networks, including the topology of connections between neurons have become an important instrument connected to the problem of processing and modelling processes. This concept results from the integration of neural networks and parameter optimization methods and makes it possible to avoid the necessity to arbitrarily define the structure of a network. This kind of extension of the training process is exemplified by the algorithm called the Group Method of Data Handling (GMDH), which belongs to the class of evolutionary algorithms. The article presents a GMDH type network, used for modelling deformations of the geometrical axis of a steel chimney during its operation.
Reifman, J.; Vitela, E.J.; Lee, J.C.
1993-03-01
Two complementary methods, statistical feature selection and nonlinear optimization through conjugate gradients, are used to expedite feedforward neural network training. Statistical feature selection techniques in the form of linear correlation coefficients and information-theoretic entropy are used to eliminate redundant and non-informative plant parameters to reduce the size of the network. The method of conjugate gradients is used to accelerate the network training convergence and to systematically calculate the Teaming and momentum constants at each iteration. The proposed techniques are compared with the backpropagation algorithm using the entire set of plant parameters in the training of neural networks to identify transients simulated with the Midland Nuclear Power Plant Unit 2 simulator. By using 25% of the plant parameters and the conjugate gradients, a 30-fold reduction in CPU time was obtained without degrading the diagnostic ability of the network.
Reifman, J. . Reactor Analysis Div.); Vitela, E.J. . Inst. de Ciencias Nucleares); Lee, J.C. . Dept. of Nuclear Engineering)
1993-01-01
Two complementary methods, statistical feature selection and nonlinear optimization through conjugate gradients, are used to expedite feedforward neural network training. Statistical feature selection techniques in the form of linear correlation coefficients and information-theoretic entropy are used to eliminate redundant and non-informative plant parameters to reduce the size of the network. The method of conjugate gradients is used to accelerate the network training convergence and to systematically calculate the Teaming and momentum constants at each iteration. The proposed techniques are compared with the backpropagation algorithm using the entire set of plant parameters in the training of neural networks to identify transients simulated with the Midland Nuclear Power Plant Unit 2 simulator. By using 25% of the plant parameters and the conjugate gradients, a 30-fold reduction in CPU time was obtained without degrading the diagnostic ability of the network.
Arab, Mohammad M.; Yadollahi, Abbas; Shojaeiyan, Abdolali; Ahmadi, Hamed
2016-01-01
One of the major obstacles to the micropropagation of Prunus rootstocks has, up until now, been the lack of a suitable tissue culture medium. Therefore, reformulation of culture media or modification of the mineral content might be a breakthrough to improve in vitro multiplication of G × N15 (garnem). We found artificial neural network in combination of genetic algorithm (ANN-GA) as a very precise and powerful modeling system for optimizing the culture medium, So that modeling the effects of MS mineral salts (NH4+, NO3-, PO42-, Ca2+, K+, SO42-, Mg2+, and Cl−) on in vitro multiplication parameters (the number of microshoots per explant, average length of microshoots, weight of calluses derived from the base of stem explants, and quality index of plantlets) of G × N15. Showed high R2 correlation values of 87, 91, 87, and 74 between observed and predicted values were found for these four growth parameters, respectively. According to the ANN-GA results, among the input variables, NH4+ and NO3- had the highest values of VSR in data set for the parameters studied. The ANN-GA showed that the best proliferation rate was obtained from medium containing (mM) 27.5 NO3-, 14 NH4+, 5 Ca2+, 25.9 K+, 0.7 Mg2+, 1.1 PO42-, 4.7 SO42-, and 0.96 Cl−. The performance of the medium optimized by ANN-GA, denoted as YAS (Yadollahi, Arab and Shojaeiyan), was compared to that of standard growth media for all Prunus rootstock, including the Murashige and Skoog (MS) medium, (specific media) EM, Quoirin and Lepoivre (QL) medium, and woody plant medium (WPM) Prunus. With respect to shoot length, shoot number per cultured explant and productivity (number of microshoots × length of microshoots), YAS was found to be superior to other media for in vitro multiplication of G × N15 rootstocks. In addition, our results indicated that by using ANN-GA, we were able to determine a suitable culture medium formulation to achieve the best in vitro productivity. PMID:27807436
Arab, Mohammad M; Yadollahi, Abbas; Shojaeiyan, Abdolali; Ahmadi, Hamed
2016-01-01
One of the major obstacles to the micropropagation of Prunus rootstocks has, up until now, been the lack of a suitable tissue culture medium. Therefore, reformulation of culture media or modification of the mineral content might be a breakthrough to improve in vitro multiplication of G × N15 (garnem). We found artificial neural network in combination of genetic algorithm (ANN-GA) as a very precise and powerful modeling system for optimizing the culture medium, So that modeling the effects of MS mineral salts ([Formula: see text], [Formula: see text], [Formula: see text], Ca(2+), K(+), [Formula: see text], Mg(2+), and Cl(-)) on in vitro multiplication parameters (the number of microshoots per explant, average length of microshoots, weight of calluses derived from the base of stem explants, and quality index of plantlets) of G × N15. Showed high R(2) correlation values of 87, 91, 87, and 74 between observed and predicted values were found for these four growth parameters, respectively. According to the ANN-GA results, among the input variables, [Formula: see text] and [Formula: see text] had the highest values of VSR in data set for the parameters studied. The ANN-GA showed that the best proliferation rate was obtained from medium containing (mM) 27.5 [Formula: see text], 14 [Formula: see text], 5 Ca(2+), 25.9 K(+), 0.7 Mg(2+), 1.1 [Formula: see text], 4.7 [Formula: see text], and 0.96 Cl(-). The performance of the medium optimized by ANN-GA, denoted as YAS (Yadollahi, Arab and Shojaeiyan), was compared to that of standard growth media for all Prunus rootstock, including the Murashige and Skoog (MS) medium, (specific media) EM, Quoirin and Lepoivre (QL) medium, and woody plant medium (WPM) Prunus. With respect to shoot length, shoot number per cultured explant and productivity (number of microshoots × length of microshoots), YAS was found to be superior to other media for in vitro multiplication of G × N15 rootstocks. In addition, our results indicated that by
Moon, Il Joon; Won, Jong Ho; Ives, D. Timothy; Nie, Kaibao; Heinz, Michael G.; Lorenzi, Christian; Rubinstein, Jay T.
2014-01-01
The dichotomy between acoustic temporal envelope (ENV) and fine structure (TFS) cues has stimulated numerous studies over the past decade to understand the relative role of acoustic ENV and TFS in human speech perception. Such acoustic temporal speech cues produce distinct neural discharge patterns at the level of the auditory nerve, yet little is known about the central neural mechanisms underlying the dichotomy in speech perception between neural ENV and TFS cues. We explored the question of how the peripheral auditory system encodes neural ENV and TFS cues in steady or fluctuating background noise, and how the central auditory system combines these forms of neural information for speech identification. We sought to address this question by (1) measuring sentence identification in background noise for human subjects as a function of the degree of available acoustic TFS information and (2) examining the optimal combination of neural ENV and TFS cues to explain human speech perception performance using computational models of the peripheral auditory system and central neural observers. Speech-identification performance by human subjects decreased as the acoustic TFS information was degraded in the speech signals. The model predictions best matched human performance when a greater emphasis was placed on neural ENV coding rather than neural TFS. However, neural TFS cues were necessary to account for the full effect of background-noise modulations on human speech-identification performance. PMID:25186758
NASA Technical Reports Server (NTRS)
Leyland, Jane Anne
2001-01-01
A closed-loop optimal neural-network controller technique was developed to optimize rotorcraft aeromechanical behaviour. This technique utilities a neural-network scheme to provide a general non-linear model of the rotorcraft. A modem constrained optimisation method is used to determine and update the constants in the neural-network plant model as well as to determine the optimal control vector. Current data is read, weighted, and added to a sliding data window. When the specified maximum number of data sets allowed in the data window is exceeded, the oldest data set is and the remaining data sets are re-weighted. This procedure provides at least four additional degrees-of-freedom in addition to the size and geometry of the neural-network itself with which to optimize the overall operation of the controller. These additional degrees-of-freedom are: 1. the maximum length of the sliding data window, 2. the frequency of neural-network updates, 3. the weighting of the individual data sets within the sliding window, and 4. the maximum number of optimisation iterations used for the neural-network updates.
NASA Technical Reports Server (NTRS)
Carpenter, William C.
1991-01-01
Engineering optimization problems involve minimizing some function subject to constraints. In areas such as aircraft optimization, the constraint equations may be from numerous disciplines such as transfer of information between these disciplines and the optimization algorithm. They are also suited to problems which may require numerous re-optimizations such as in multi-objective function optimization or to problems where the design space contains numerous local minima, thus requiring repeated optimizations from different initial designs. Their use has been limited, however, by the fact that development of response surfaces randomly selected or preselected points in the design space. Thus, they have been thought to be inefficient compared to algorithms to the optimum solution. A development has taken place in the last several years which may effect the desirability of using response surfaces. It may be possible that artificial neural nets are more efficient in developing response surfaces than polynomial approximations which have been used in the past. This development is the concern of the work.
Rule extraction from an optimized neural network for traffic crash frequency modeling.
Zeng, Qiang; Huang, Helai; Pei, Xin; Wong, S C; Gao, Mingyun
2016-12-01
This study develops a neural network (NN) model to explore the nonlinear relationship between crash frequency and risk factors. To eliminate the possibility of over-fitting and to deal with the black-box characteristic, a network structure optimization algorithm and a rule extraction method are proposed. A case study compares the performance of the trained and modified NN models with that of the traditional negative binomial (NB) model for analyzing crash frequency on road segments in Hong Kong. The results indicate that the optimized NNs have somewhat better fitting and predictive performance than the NB models. Moreover, the smaller training/testing errors in the optimized NNs with pruned input and hidden nodes demonstrate the ability of the structure optimization algorithm to identify the insignificant factors and to improve the model generalization capacity. Furthermore, the rule-set extracted from the optimized NN model can reveal the effect of each explanatory variable on the crash frequency under different conditions, and implies the existence of nonlinear relationship between factors and crash frequency. With the structure optimization algorithm and rule extraction method, the modified NN model has great potential for modeling crash frequency, and may be considered as a good alternative for road safety analysis.
Wei, Hua-Liang; Billings, Stephen A; Zhao, Yifan; Guo, Lingzhong
2009-01-01
In this brief, by combining an efficient wavelet representation with a coupled map lattice model, a new family of adaptive wavelet neural networks, called lattice dynamical wavelet neural networks (LDWNNs), is introduced for spatio-temporal system identification. A new orthogonal projection pursuit (OPP) method, coupled with a particle swarm optimization (PSO) algorithm, is proposed for augmenting the proposed network. A novel two-stage hybrid training scheme is developed for constructing a parsimonious network model. In the first stage, by applying the OPP algorithm, significant wavelet neurons are adaptively and successively recruited into the network, where adjustable parameters of the associated wavelet neurons are optimized using a particle swarm optimizer. The resultant network model, obtained in the first stage, however, may be redundant. In the second stage, an orthogonal least squares algorithm is then applied to refine and improve the initially trained network by removing redundant wavelet neurons from the network. An example for a real spatio-temporal system identification problem is presented to demonstrate the performance of the proposed new modeling framework.
Cao, Jianfang; Cui, Hongyan; Shi, Hao; Jiao, Lijuan
2016-01-01
A back-propagation (BP) neural network can solve complicated random nonlinear mapping problems; therefore, it can be applied to a wide range of problems. However, as the sample size increases, the time required to train BP neural networks becomes lengthy. Moreover, the classification accuracy decreases as well. To improve the classification accuracy and runtime efficiency of the BP neural network algorithm, we proposed a parallel design and realization method for a particle swarm optimization (PSO)-optimized BP neural network based on MapReduce on the Hadoop platform using both the PSO algorithm and a parallel design. The PSO algorithm was used to optimize the BP neural network's initial weights and thresholds and improve the accuracy of the classification algorithm. The MapReduce parallel programming model was utilized to achieve parallel processing of the BP algorithm, thereby solving the problems of hardware and communication overhead when the BP neural network addresses big data. Datasets on 5 different scales were constructed using the scene image library from the SUN Database. The classification accuracy of the parallel PSO-BP neural network algorithm is approximately 92%, and the system efficiency is approximately 0.85, which presents obvious advantages when processing big data. The algorithm proposed in this study demonstrated both higher classification accuracy and improved time efficiency, which represents a significant improvement obtained from applying parallel processing to an intelligent algorithm on big data.
Cao, Jianfang; Cui, Hongyan; Shi, Hao; Jiao, Lijuan
2016-01-01
A back-propagation (BP) neural network can solve complicated random nonlinear mapping problems; therefore, it can be applied to a wide range of problems. However, as the sample size increases, the time required to train BP neural networks becomes lengthy. Moreover, the classification accuracy decreases as well. To improve the classification accuracy and runtime efficiency of the BP neural network algorithm, we proposed a parallel design and realization method for a particle swarm optimization (PSO)-optimized BP neural network based on MapReduce on the Hadoop platform using both the PSO algorithm and a parallel design. The PSO algorithm was used to optimize the BP neural network’s initial weights and thresholds and improve the accuracy of the classification algorithm. The MapReduce parallel programming model was utilized to achieve parallel processing of the BP algorithm, thereby solving the problems of hardware and communication overhead when the BP neural network addresses big data. Datasets on 5 different scales were constructed using the scene image library from the SUN Database. The classification accuracy of the parallel PSO-BP neural network algorithm is approximately 92%, and the system efficiency is approximately 0.85, which presents obvious advantages when processing big data. The algorithm proposed in this study demonstrated both higher classification accuracy and improved time efficiency, which represents a significant improvement obtained from applying parallel processing to an intelligent algorithm on big data. PMID:27304987
Electronic neural network for solving traveling salesman and similar global optimization problems
NASA Technical Reports Server (NTRS)
Thakoor, Anilkumar P. (Inventor); Moopenn, Alexander W. (Inventor); Duong, Tuan A. (Inventor); Eberhardt, Silvio P. (Inventor)
1993-01-01
This invention is a novel high-speed neural network based processor for solving the 'traveling salesman' and other global optimization problems. It comprises a novel hybrid architecture employing a binary synaptic array whose embodiment incorporates the fixed rules of the problem, such as the number of cities to be visited. The array is prompted by analog voltages representing variables such as distances. The processor incorporates two interconnected feedback networks, each of which solves part of the problem independently and simultaneously, yet which exchange information dynamically.
Using recurrent neural networks to optimize dynamical decoupling for quantum memory
NASA Astrophysics Data System (ADS)
August, Moritz; Ni, Xiaotong
2017-01-01
We utilize machine learning models that are based on recurrent neural networks to optimize dynamical decoupling (DD) sequences. Dynamical decoupling is a relatively simple technique for suppressing the errors in quantum memory for certain noise models. In numerical simulations, we show that with minimum use of prior knowledge and starting from random sequences, the models are able to improve over time and eventually output DD sequences with performance better than that of the well known DD families. Furthermore, our algorithm is easy to implement in experiments to find solutions tailored to the specific hardware, as it treats the figure of merit as a black box.
NASA Astrophysics Data System (ADS)
Wang, Dianhui; Dillon, T. S.
2001-03-01
Extracting and optimizing rules from continuous or mixed- mode data directly for pattern classification problems is a challenging problem. Self-organizing neural-nets are employed to initialize the rules. A regularization model which trades off misclassification rate, recognition rate and generalization ability is first presented for refining the initial rules. To generate rules for patterns with lower probability density but considerable conceptual importance, an approach to iteratively resolving the clustering part for a filtered set of data is used. The methodology is evaluated using Iris data and demonstrates the effectiveness of technique.
NASA Astrophysics Data System (ADS)
Okada, N.; Nojima, K.; Ishibashi, N.; Nagatoshi, K.; Itagaki, N.; Inomoto, R.; Motoyama, S.; Kobayashi, T.; Tadatomo, K.
2017-06-01
We focused on inductively coupled plasma and reactive ion etching (ICP-RIE) for etching GaN and tried to fabricate distinctive GaN structures under optimized chemical etching conditions. To determine the optimum chemical etching conditions, the flow rates of Ar and Cl2, ICP power, and chamber pressure were varied in the etching of c-plane GaN layers with stripe patterns. It was determined that the combination of Ar and Cl2 flow rates of 100 sccm, chamber pressure of 7 Pa, and ICP power of 800 W resulted in the most enhanced reaction, yielding distinctive GaN structures such as pillars with inverted mesa structures for c-plane GaN and a semipolar GaN layer with asymmetric inclined sidewalls. The selectivity and etching rate were also investigated.
Optimal path-finding through mental exploration based on neural energy field gradients.
Wang, Yihong; Wang, Rubin; Zhu, Yating
2017-02-01
Rodent animal can accomplish self-locating and path-finding task by forming a cognitive map in the hippocampus representing the environment. In the classical model of the cognitive map, the system (artificial animal) needs large amounts of physical exploration to study spatial environment to solve path-finding problems, which costs too much time and energy. Although Hopfield's mental exploration model makes up for the deficiency mentioned above, the path is still not efficient enough. Moreover, his model mainly focused on the artificial neural network, and clear physiological meanings has not been addressed. In this work, based on the concept of mental exploration, neural energy coding theory has been applied to the novel calculation model to solve the path-finding problem. Energy field is constructed on the basis of the firing power of place cell clusters, and the energy field gradient can be used in mental exploration to solve path-finding problems. The study shows that the new mental exploration model can efficiently find the optimal path, and present the learning process with biophysical meaning as well. We also analyzed the parameters of the model which affect the path efficiency. This new idea verifies the importance of place cell and synapse in spatial memory and proves that energy coding is effective to study cognitive activities. This may provide the theoretical basis for the neural dynamics mechanism of spatial memory.
Mayorga, René V; Arriaga, Mariano
2007-10-01
In this article, a novel technique for non-linear global optimization is presented. The main goal is to find the optimal global solution of non-linear problems avoiding sub-optimal local solutions or inflection points. The proposed technique is based on a two steps concept: properly keep decreasing the value of the objective function, and calculating the corresponding independent variables by approximating its inverse function. The decreasing process can continue even after reaching local minima and, in general, the algorithm stops when converging to solutions near the global minimum. The implementation of the proposed technique by conventional numerical methods may require a considerable computational effort on the approximation of the inverse function. Thus, here a novel Artificial Neural Network (ANN) approach is implemented to reduce the computational requirements of the proposed optimization technique. This approach is successfully tested on some highly non-linear functions possessing several local minima. The results obtained demonstrate that the proposed approach compares favorably over some current conventional numerical (Matlab functions) methods, and other non-conventional (Evolutionary Algorithms, Simulated Annealing) optimization methods.
Crop Classification by Forward Neural Network with Adaptive Chaotic Particle Swarm Optimization
Zhang, Yudong; Wu, Lenan
2011-01-01
This paper proposes a hybrid crop classifier for polarimetric synthetic aperture radar (SAR) images. The feature sets consisted of span image, the H/A/α decomposition, and the gray-level co-occurrence matrix (GLCM) based texture features. Then, the features were reduced by principle component analysis (PCA). Finally, a two-hidden-layer forward neural network (NN) was constructed and trained by adaptive chaotic particle swarm optimization (ACPSO). K-fold cross validation was employed to enhance generation. The experimental results on Flevoland sites demonstrate the superiority of ACPSO to back-propagation (BP), adaptive BP (ABP), momentum BP (MBP), Particle Swarm Optimization (PSO), and Resilient back-propagation (RPROP) methods. Moreover, the computation time for each pixel is only 1.08 × 10−7 s. PMID:22163872
Crop classification by forward neural network with adaptive chaotic particle swarm optimization.
Zhang, Yudong; Wu, Lenan
2011-01-01
This paper proposes a hybrid crop classifier for polarimetric synthetic aperture radar (SAR) images. The feature sets consisted of span image, the H/A/α decomposition, and the gray-level co-occurrence matrix (GLCM) based texture features. Then, the features were reduced by principle component analysis (PCA). Finally, a two-hidden-layer forward neural network (NN) was constructed and trained by adaptive chaotic particle swarm optimization (ACPSO). K-fold cross validation was employed to enhance generation. The experimental results on Flevoland sites demonstrate the superiority of ACPSO to back-propagation (BP), adaptive BP (ABP), momentum BP (MBP), Particle Swarm Optimization (PSO), and Resilient back-propagation (RPROP) methods. Moreover, the computation time for each pixel is only 1.08 × 10(-7) s.
NASA Astrophysics Data System (ADS)
Tapoglou, E.; Trichakis, I. C.; Dokou, Z.; Karatzas, G. P.
2012-04-01
The purpose of this study is to examine the use of particle swarm optimization algorithm in order to train a feed-forward multi-layer artificial neural network, which can simulate hydraulic head change at an observation well. Particle swarm optimization is a relatively new evolutionary algorithm, developed by Eberhart and Kennedy (1995), which is used to find optimal solutions to numerical and quantitative problems. Three different variations of particle swarm optimization algorithm are considered, the classic algorithm with the improvement of inertia weight, PSO-TVAC and GLBest-PSO. The best performance among all the algorithms was achieved by GLBest-PSO, where the distance between the overall best solution found and the best solution of each particle plays a major role in updating each particle's velocity. The algorithm is implemented using field data from the region of Agia, Chania, Greece. The particle swarm optimization algorithm shows an improvement of 9.3% and 18% in training and test errors respectively, compared to the errors of the back propagation algorithm. The trained neural network can predict the hydraulic head change at a well, without being able to predict extreme and transitional phenomena. The maximum divergence from the observed values is 0.35m. When the hydraulic head change is converted into hydraulic head, using the observed hydraulic head of the previous day, the deviations of simulated values from the actual hydraulic head appear comparatively smaller, with an average deviation of 0.041m. The trained neural network was also used for midterm prediction. In this case, the hydraulic head of the first day of the simulation is used together with the hydraulic head change derived from the simulation. The values obtained by this process were smaller than the observed, while the maximum difference is approximately 1m. However, this error, is not accumulated during the two hydrological years of simulation, and the error at the end of the simulation
2014-01-01
An extensive study on molecular beam epitaxy growth conditions of quaternary GaAsSbN as a capping layer (CL) for InAs/GaAs quantum dots (QD) was carried out. In particular, CL thickness, growth temperature, and growth rate were optimized. Problems related to the simultaneous presence of Sb and N, responsible for a significant degradation of photoluminescence (PL), are thereby solved allowing the achievement of room-temperature (RT) emission. A particularly strong improvement on the PL is obtained when the growth rate of the CL is increased. This is likely due to an improvement in the structural quality of the quaternary alloy that resulted from reduced strain and composition inhomogeneities. Nevertheless, a significant reduction of Sb and N incorporation was found when the growth rate was increased. Indeed, the incorporation of N is intrinsically limited to a maximum value of approximately 1.6% when the growth rate is at 2.0 ML s−1. Therefore, achieving RT emission and extending it somewhat beyond 1.3 μm were possible by means of a compromise among the growth conditions. This opens the possibility of exploiting the versatility on band structure engineering offered by this QD-CL structure in devices working at RT. PACS 81.15.Hi (molecular beam epitaxy); 78.55.Cr (III-V semiconductors); 73.21.La (quantum dots) PMID:24438542
Utrilla, Antonio D; Ulloa, Jose M; Guzman, Alvaro; Hierro, Adrian
2014-01-17
An extensive study on molecular beam epitaxy growth conditions of quaternary GaAsSbN as a capping layer (CL) for InAs/GaAs quantum dots (QD) was carried out. In particular, CL thickness, growth temperature, and growth rate were optimized. Problems related to the simultaneous presence of Sb and N, responsible for a significant degradation of photoluminescence (PL), are thereby solved allowing the achievement of room-temperature (RT) emission. A particularly strong improvement on the PL is obtained when the growth rate of the CL is increased. This is likely due to an improvement in the structural quality of the quaternary alloy that resulted from reduced strain and composition inhomogeneities. Nevertheless, a significant reduction of Sb and N incorporation was found when the growth rate was increased. Indeed, the incorporation of N is intrinsically limited to a maximum value of approximately 1.6% when the growth rate is at 2.0 ML s-1. Therefore, achieving RT emission and extending it somewhat beyond 1.3 μm were possible by means of a compromise among the growth conditions. This opens the possibility of exploiting the versatility on band structure engineering offered by this QD-CL structure in devices working at RT. PACS: 81.15.Hi (molecular beam epitaxy); 78.55.Cr (III-V semiconductors); 73.21.La (quantum dots).
NASA Astrophysics Data System (ADS)
Ghaffari Razin, Mir Reza; Voosoghi, Behzad
2016-11-01
Wavelet neural networks (WNNs) are a new class of neural networks (NNs) that has been developed using a combined method of multi-layer artificial neural networks and wavelet analysis (WA). In this paper, WNNs is used for modeling and prediction of total electron content (TEC) of ionosphere with high spatial and temporal resolution. Generally, back-propagation (BP) algorithm is used to train the neural network. While this algorithm proves to be very effective and robust in training many types of network structures, it suffers from certain disadvantages such as easy entrapment in a local minimum and slow convergence. To improve the performance of WNN in training step, the adjustment of network weights using particle swarm optimization (PSO) was proposed. The results obtained in this paper were compared with standard NN (SNN) by BP training algorithm (SNN-BP), SNN by PSO training algorithm (SNN-PSO) and WNN by BP training algorithm (WNN-BP). For numerical experiments, observations collected at 36 GPS stations in 5 days of 2012 from Iranian permanent GPS network (IPGN) are used. The average minimum relative errors in 5 test stations for WNN-PSO, WNN-BP, SNN-BP and SNN-PSO compared with GPS TEC are 10.59%, 12.85%, 13.18%, 13.75% and average maximum relative errors are 14.70%, 17.30%, 18.53% and 20.83%, respectively. Comparison of diurnal predicted TEC values from the WNN-PSO, SNN-BP, SNN-PSO and WNN-BP models with GPS TEC revealed that the WNN-PSO provides more accurate predictions than the other methods in the test area.
Park, Se-Ra; Lim, Chae-Yeon; Kim, Deuk-Su; Ko, Kisung
2015-01-01
A protein purification procedure is required to obtain high-value recombinant injectable vaccine proteins produced in plants as a bioreactor. However, existing purification procedures for plant-derived recombinant proteins are often not optimized and are inefficient, with low recovery rates. In our previous study, we used 25-30% ammonium sulfate to precipitate total soluble proteins (TSPs) in purification process for recombinant proteins from plant leaf biomass which has not been optimized. Thus, the objective in this study is to optimize the conditions for plant-derived protein purification procedures. Various ammonium sulfate concentrations (15-80%) were compared to determine their effects on TSPs yield. With 50% ammonium sulfate, the yield of precipitated TSP was the highest, and that of the plant-derived colorectal cancer-specific surface glycoprotein GA733 fused to the Fc fragment of human IgG tagged with endoplasmic reticulum retention signal KDEL (GA733(P)-FcK) protein significantly increased 1.8-fold. SDS-PAGE analysis showed that the purity of GA733(P)-FcK protein band appeared to be similar to that of an equal dose of mammalian-derived GA733-Fc (GA733(M)-Fc). The binding activity of purified GA733(P)-FcK to anti-GA733 mAb was as efficient as the native GA733(M)-Fc. Thus, the purification process was effectively optimized for obtaining a high yield of plant-derived antigenic protein with good quality. In conclusion, the purification recovery rate of large quantities of recombinant protein from plant expression systems can be enhanced via optimization of ammonium sulfate concentration during downstream processes, thereby offering a promising solution for production of recombinant GA733-Fc protein in plants.
Smoothing neural network for constrained non-Lipschitz optimization with applications.
Bian, Wei; Chen, Xiaojun
2012-03-01
In this paper, a smoothing neural network (SNN) is proposed for a class of constrained non-Lipschitz optimization problems, where the objective function is the sum of a nonsmooth, nonconvex function, and a non-Lipschitz function, and the feasible set is a closed convex subset of . Using the smoothing approximate techniques, the proposed neural network is modeled by a differential equation, which can be implemented easily. Under the level bounded condition on the objective function in the feasible set, we prove the global existence and uniform boundedness of the solutions of the SNN with any initial point in the feasible set. The uniqueness of the solution of the SNN is provided under the Lipschitz property of smoothing functions. We show that any accumulation point of the solutions of the SNN is a stationary point of the optimization problem. Numerical results including image restoration, blind source separation, variable selection, and minimizing condition number are presented to illustrate the theoretical results and show the efficiency of the SNN. Comparisons with some existing algorithms show the advantages of the SNN.
Neural Network-Based Solutions for Stochastic Optimal Control Using Path Integrals.
Rajagopal, Karthikeyan; Balakrishnan, Sivasubramanya Nadar; Busemeyer, Jerome R
2017-03-01
In this paper, an offline approximate dynamic programming approach using neural networks is proposed for solving a class of finite horizon stochastic optimal control problems. There are two approaches available in the literature, one based on stochastic maximum principle (SMP) formalism and the other based on solving the stochastic Hamilton-Jacobi-Bellman (HJB) equation. However, in the presence of noise, the SMP formalism becomes complex and results in having to solve a couple of backward stochastic differential equations. Hence, current solution methodologies typically ignore the noise effect. On the other hand, the inclusion of noise in the HJB framework is very straightforward. Furthermore, the stochastic HJB equation of a control-affine nonlinear stochastic system with a quadratic control cost function and an arbitrary state cost function can be formulated as a path integral (PI) problem. However, due to curse of dimensionality, it might not be possible to utilize the PI formulation for obtaining comprehensive solutions over the entire operating domain. A neural network structure called the adaptive critic design paradigm is used to effectively handle this difficulty. In this paper, a novel adaptive critic approach using the PI formulation is proposed for solving stochastic optimal control problems. The potential of the algorithm is demonstrated through simulation results from a couple of benchmark problems.
Initialization and self-organized optimization of recurrent neural network connectivity.
Boedecker, Joschka; Obst, Oliver; Mayer, N Michael; Asada, Minoru
2009-10-01
Reservoir computing (RC) is a recent paradigm in the field of recurrent neural networks. Networks in RC have a sparsely and randomly connected fixed hidden layer, and only output connections are trained. RC networks have recently received increased attention as a mathematical model for generic neural microcircuits to investigate and explain computations in neocortical columns. Applied to specific tasks, their fixed random connectivity, however, leads to significant variation in performance. Few problem-specific optimization procedures are known, which would be important for engineering applications, but also in order to understand how networks in biology are shaped to be optimally adapted to requirements of their environment. We study a general network initialization method using permutation matrices and derive a new unsupervised learning rule based on intrinsic plasticity (IP). The IP-based learning uses only local learning, and its aim is to improve network performance in a self-organized way. Using three different benchmarks, we show that networks with permutation matrices for the reservoir connectivity have much more persistent memory than the other methods but are also able to perform highly nonlinear mappings. We also show that IP-based on sigmoid transfer functions is limited concerning the output distributions that can be achieved.
Kaiser, Marcus; Hilgetag, Claus C.
2009-01-01
An essential requirement for the representation of functional patterns in complex neural networks, such as the mammalian cerebral cortex, is the existence of stable regimes of network activation, typically arising from a limited parameter range. In this range of limited sustained activity (LSA), the activity of neural populations in the network persists between the extremes of either quickly dying out or activating the whole network. Hierarchical modular networks were previously found to show a wider parameter range for LSA than random or small-world networks not possessing hierarchical organization or multiple modules. Here we explored how variation in the number of hierarchical levels and modules per level influenced network dynamics and occurrence of LSA. We tested hierarchical configurations of different network sizes, approximating the large-scale networks linking cortical columns in one hemisphere of the rat, cat, or macaque monkey brain. Scaling of the network size affected the number of hierarchical levels and modules in the optimal networks, also depending on whether global edge density or the numbers of connections per node were kept constant. For constant edge density, only few network configurations, possessing an intermediate number of levels and a large number of modules, led to a large range of LSA independent of brain size. For a constant number of node connections, there was a trend for optimal configurations in larger-size networks to possess a larger number of hierarchical levels or more modules. These results may help to explain the trend to greater network complexity apparent in larger brains and may indicate that this complexity is required for maintaining stable levels of neural activation. PMID:20514144
Eppard, Elisabeth; Homann, Tatjana; de la Fuente, Ana; Essler, Markus; Rösch, Frank
2017-03-01
Radiolabeling of the prostate-specific membrane antigen (PSMA) inhibitor Glu-NH-CO-NH-Lys(Ahx) using the (68)Ga chelator HBED-CC (PSMA(HBED)) allows imaging of prostate cancer lesions because of high expression of PSMA in prostate carcinoma cells and in bone metastases and lymph nodes related to the disease. The aim of this work was to optimize labeling of (68)Ga-PSMA(HBED) using the efficient cation-exchange postprocessing of (68)Ga as well as the development of a thin-layer chromatography (TLC)-based quality control system. Methods: Labeling was optimized for online ethanol-postprocessed (68)Ga eluate investigating various parameters, such as buffer molarity (0.1-1 M), temperature (25°C-90°C), tracer amount (0.11-0.74 nmol), and labeling time. In addition, purification of the crude product was tested. For radio-TLC quality control, various mobile phases were analyzed using silica gel 60 plates and the results were validated using high-performance liquid chromatography. The most superior mobile phases were also applied on instant thin-layer chromatography (ITLC) silica gel plates. Results: Using optimized conditions, labeling yields of more than 95% were obtained within 10 min when ethanol-based postprocessing was applied using PSMA(HBED) amounts as low as 0.1 nmol. A higher precursor concentration (0.7 nmol) further increased labeling and quantitative yields to more than 98% within 5 min. In clinical routine, patient batches (>200 applications) with radiochemical purity greater than 98% and specific activities of 326 ± 20 MBq/nmol are obtained reproducibly. When TLC quality control was performed on silica gel 60 plates, 4 mobile phases with suitable separation properties and complementary Rf values were identified. Two systems showed equivalent separation on ITLC silica gel plates, with ITLC analysis finished within 5 min, in contrast to 20 min for the TLC system. Labeling of PSMA(HBED) was optimized for cation-exchange postprocessing methods, ensuring almost
NASA Astrophysics Data System (ADS)
Lazzús, J. A.; López-Caraballo, C. H.; Rojas, P.; Salfate, I.; Rivera, M.; Palma-Chilla, L.
2016-05-01
In this study, an artificial neural network was optimized with particle swarm algorithm and trained to predict the geomagmetic DST index one hour ahead using the past values of DST and auroral electrojet indices. The results show that the proposed neural network model can be properly trained for predicting of DST(t + 1) with acceptable accuracy, and that the geomagnetic indices used have influential effects on the good training and predicting capabilities of the chosen network.
One-step production of optimized Fe-Ga particles by spark erosion
Hong, J. I.; Solomon, V. C.; Smith, David J.; Parker, F. T.; Summers, E. M.; Berkowitz, A. E.
2006-10-02
Spherical Fe-Ga particles were prepared by spark erosion in liquid Ar, which directly incorporated the desirable rapid quench from high temperatures. The compositions of the particles investigated were 15.0, 16.3, and 18.9 at. % Ga, respectively, as determined from electron-probe microanalysis, x-ray diffraction, and Moessbauer spectra. Composites for magnetostriction measurements were prepared by mixing particles with epoxy at the volume fraction of 48% and curing in a magnetic field. Magnetostriction values of the composites were comparable to those of polycrystalline chill-cast alloys of the same compositions. Composites with particles having Ga concentrations of 18.9 at. % had the highest magnetostriction, similar to results reported for bulk Fe-Ga alloys.
Optimal width of quantum well for reversed polarization blue InGaN light-emitting diodes
NASA Astrophysics Data System (ADS)
Kang, Junjie; Li, Zhi; Li, Hongjian; Liu, Zhiqiang; Ma, Ping; Yi, Xiaoyan; Wang, Guohong
2013-07-01
The optical properties of reversed polarization (RP) blue InGaN light-emitting diodes (LEDs) under different quantum wells (QWs) width are numerically studied. We compared the band diagram, electron and hole concentration, emission wavelength, radiation recombination, internal quantum efficiency (IQE), turn on voltage and light output power (LOP) of these structures by numerical simulation. It found that QW width has a remarkable influence on the properties of RP blue InGaN LEDs. With the increase of QW width, the turn on voltage and radiation recombination rate decreases. It finds that the optimal width of QWs is about 3 nm at the current injection density of 15 A/cm2.
NASA Astrophysics Data System (ADS)
Lin, Chia-Hung; Abe, Ryota; Uchiyama, Shota; Maruyama, Takahiro; Naritsuka, Shigeya
2012-08-01
Growth optimization toward low angle incidence microchannel epitaxy (LAIMCE) of GaN was accomplished using ammonia-based metal-organic molecular beam epitaxy (NH3-based MOMBE). Firstly, the [NH3]/[trimethylgallium (TMG)] ratio (R) dependence of selective GaN growth was studied. The growth temperature was set at 860 °C while R was varied from 5 to 200 with precursors being supplied parallel to the openings cut in the SiO2 mask. The selectivity of the growth was superior for all R, because TMG and NH3 preferably decompose on the GaN film. The formation of {112¯0}GaN or {112¯2}GaN sidewalls and (0001)GaN surface were observed by the change in R. The intersurface diffusion of Ga adatoms was also changed by a change in R. Ga adatoms migrate from the sidewalls to the top at R lower than 50, whereas the migration weakened with R greater than 100. Secondly, LAIMCE was optimized by changing the growth temperature. Consequently, 6 μm wide lateral overgrowth in the direction of precursor incidence was achieved with no pit after etching by H3PO4, which was six times wider than that in the opposite direction.
Hage, Ilige S; Hamade, Ramsey F
2013-01-01
The aim of this study is to automatically discern the micro-features in histology slides of cortical bone using pulse coupled neural networks (PCNN). To the best knowledge of the authors, utilizing PCNN in such an application has not been reported in the literature and, as such, constitutes a novel application. The network parameters are optimized using particle swarm optimization (PSO) where the PSO fitness function was introduced as the entropy and energy of the bone micro-constituents extracted from a training image. Another novel contribution is combining the above with the method of adaptive threshold (T) where the PCNN algorithm is repeated until the best threshold T is found corresponding to the maximum variance between two segmented regions. To illustrate the quality of resulting segmentation according to this methodology, a comparison of the entropy/energy obtained of each pulse is reported. Suitable quality metrics (precision rate, sensitivity, specificity, accuracy, and dice) were used to benchmark the resulting segments against those found by a more traditional method namely K-means. The quality of the segments revealed by this methodology was found to be of much superior quality. Another testament to the quality of this methodology was that the images resulting from testing pulses were found to be of similarly good quality to those of the training images.
Xu, Hao; Jagannathan, Sarangapani
2015-03-01
The stochastic optimal control of nonlinear networked control systems (NNCSs) using neuro-dynamic programming (NDP) over a finite time horizon is a challenging problem due to terminal constraints, system uncertainties, and unknown network imperfections, such as network-induced delays and packet losses. Since the traditional iteration or time-based infinite horizon NDP schemes are unsuitable for NNCS with terminal constraints, a novel time-based NDP scheme is developed to solve finite horizon optimal control of NNCS by mitigating the above-mentioned challenges. First, an online neural network (NN) identifier is introduced to approximate the control coefficient matrix that is subsequently utilized in conjunction with the critic and actor NNs to determine a time-based stochastic optimal control input over finite horizon in a forward-in-time and online manner. Eventually, Lyapunov theory is used to show that all closed-loop signals and NN weights are uniformly ultimately bounded with ultimate bounds being a function of initial conditions and final time. Moreover, the approximated control input converges close to optimal value within finite time. The simulation results are included to show the effectiveness of the proposed scheme.
Chang, P.S.; Poston, J.
1996-07-01
Boiler performance optimization includes the preservation of efficiency, emission, capacity, and reliability. Competitive pressures require cost reduction and environmental compliance. It is a challenge for utility personnel to balance these requirements and to achieve specific company goals. Unfortunately, these requirements often demand tradeoffs. The Clean Air Act Amendment requires Utilities to reduce NO{sub x} emission. NO{sub x} emission reduction has often been accomplished by installation of new low NO{sub x} burners. Boiler tuning for NO{sub x} control can be used as an alternative to low NO{sub x} burner installation. A PC-based computer software program was developed to assist the tuning process. This software, System Optimization Analysis Program (SOAP), is a neural network based code which uses the self-adaptation learning process, with an adaptive filter added for data noise control. SOAP can use historical data as the knowledge base and it provides a fast optimal solution to adaptive control problems. SOAP was tested at several fossil plants. The tests were primarily for NO{sub x} reduction, but the performance parameters were optimized simultaneously.
Feng, Ruibin; Leung, Chi-Sing; Constantinides, Anthony G; Zeng, Wen-Jun
2016-07-27
The major limitation of the Lagrange programming neural network (LPNN) approach is that the objective function and the constraints should be twice differentiable. Since sparse approximation involves nondifferentiable functions, the original LPNN approach is not suitable for recovering sparse signals. This paper proposes a new formulation of the LPNN approach based on the concept of the locally competitive algorithm (LCA). Unlike the classical LCA approach which is able to solve unconstrained optimization problems only, the proposed LPNN approach is able to solve the constrained optimization problems. Two problems in sparse approximation are considered. They are basis pursuit (BP) and constrained BP denoise (CBPDN). We propose two LPNN models, namely, BP-LPNN and CBPDN-LPNN, to solve these two problems. For these two models, we show that the equilibrium points of the models are the optimal solutions of the two problems, and that the optimal solutions of the two problems are the equilibrium points of the two models. Besides, the equilibrium points are stable. Simulations are carried out to verify the effectiveness of these two LPNN models.
NASA Astrophysics Data System (ADS)
Gao, Xin-jiang; Tang, Zun-lie; Zhang, Xiu-chuan; Chen, Yang; Jiang, Li-qun; Cheng, Hong-bing
2009-07-01
Significant progress has been achieved in technology of the InGaAs focal plane arrays (FPA) detector operating in short wave infrared (SWIR) last two decades. The no cryogenic cooling, low manufacturing cost, low power, high sensitivity and maneuverability features inherent of InGaAs FPA make it as a mainstream SWIR FPA in a variety of critical military, national security, aerospace, telecommunications and industrial applications. These various types of passive image sensing or active illumination image detecting systems included range-gated imaging, 3-Dimensional Ladar, covert surveillance, pulsed laser beam profiling, machine vision, semiconductor inspection, free space optical communications beam tracker, hyperspectroscopy imaging and many others. In this paper the status and perspectives of hybrid InGaAs FPA which is composed of detector array (PDA) and CMOS readout integrate circuit (ROIC) are reviewed briefly. For various low light levels applications such as starlight or night sky illumination, we have made use of the interface circuit of capacitive feedback transimpedance amplifier (CTIA) in which the integration capacitor was adjustable, therefore implements of the physical and electrical characteristics matches between detector arrays and readout intergrate circuit was achieved excellently. Taking into account the influences of InGaAs detector arrays' optoelectronic characteristics on performance of the FPA, we discussed the key parameters of the photodiode in detailed, and the tradeoff between the responsivity, dark current, impedance at zero bias and junction capacitance of photosensitive element has been made to root out the impact factors. As a result of the educed approach of the photodiode's characteristics optimizing which involve with InGaAs PDA design and process, a high performance InGaAs FPA of 30um pixel pitch and 320×256 format has been developed of which the response spectrum range over 0.9um to 1.7um, the mean peak detectivity (λ=1.55
Poultangari, Iman; Shahnazi, Reza; Sheikhan, Mansour
2012-09-01
In order to control the pitch angle of blades in wind turbines, commonly the proportional and integral (PI) controller due to its simplicity and industrial usability is employed. The neural networks and evolutionary algorithms are tools that provide a suitable ground to determine the optimal PI gains. In this paper, a radial basis function (RBF) neural network based PI controller is proposed for collective pitch control (CPC) of a 5-MW wind turbine. In order to provide an optimal dataset to train the RBF neural network, particle swarm optimization (PSO) evolutionary algorithm is used. The proposed method does not need the complexities, nonlinearities and uncertainties of the system under control. The simulation results show that the proposed controller has satisfactory performance.
Fjodorova, Natalja; Novič, Marjana
2015-09-03
Engineering optimization is an actual goal in manufacturing and service industries. In the tutorial we represented the concept of traditional parametric estimation models (Factorial Design (FD) and Central Composite Design (CCD)) for searching optimal setting parameters of technological processes. Then the 2D mapping method based on Auto Associative Neural Networks (ANN) (particularly, the Feed Forward Bottle Neck Neural Network (FFBN NN)) was described in comparison with traditional methods. The FFBN NN mapping technique enables visualization of all optimal solutions in considered processes due to the projection of input as well as output parameters in the same coordinates of 2D map. This phenomenon supports the more efficient way of improving the performance of existing systems. Comparison of two methods was performed on the bases of optimization of solder paste printing processes as well as optimization of properties of cheese. Application of both methods enables the double check. This increases the reliability of selected optima or specification limits.
Vlassides, S; Ferrier, J G; Block, D E
2001-04-05
Optimization of fermentation processes is a difficult task that relies on an understanding of the complex effects of processing inputs on productivity and quality outputs. Because of the complexity of these biological systems, traditional optimization methods utilizing mathematical models and statistically designed experiments are less effective, especially on a production scale. At the same time, information is being collected on a regular basis during the course of normal manufacturing and process development that is rarely fully utilized. We are developing an optimization method in which historical process data is used to train an artificial neural network for correlation of processing inputs and outputs. Subsequently, an optimization routine is used in conjunction with the trained neural network to find optimal processing conditions given the desired product characteristics and any constraints on inputs. Wine processing is being used as a case study for this work. Using data from wine produced in our pilot winery over the past 3 years, we have demonstrated that trained neural networks can be used successfully to predict the yeast-fermentation kinetics, as well as chemical and sensory properties of the finished wine, based solely on the properties of the grapes and the intended processing. To accomplish this, a hybrid neural network training method, Stop Training with Validation (STV), has been developed to find the most desirable neural network architecture and training level. As industrial historical data will not be evenly spaced over the entire possible search space, we have also investigated the ability of the trained neural networks to interpolate and extrapolate with data not used during training. Because a company will utilize its own existing process data for this method, the result of this work will be a general fermentation optimization method that can be applied to fermentation processes to improve quality and productivity.
Liu, Long; Sun, Jun; Xu, Wenbo; Du, Guocheng; Chen, Jian
2009-01-01
Hyaluronic acid (HA) is a natural biopolymer with unique physiochemical and biological properties and finds a wide range of applications in biomedical and cosmetic fields. It is important to increase HA production to meet the increasing HA market demand. This work is aimed to model and optimize the amino acids addition to enhance HA production of Streptococcus zooepidemicus with radial basis function (RBF) neural network coupling quantum-behaved particle swarm optimization (QPSO) algorithm. In the RBF-QPSO approach, RBF neural network is used as a bioprocess modeling tool and QPSO algorithm is applied to conduct the optimization with the established RBF neural network black model as the objective function. The predicted maximum HA yield was 6.92 g/L under the following conditions: arginine 0.062 g/L, cysteine 0.036 g/L, and lysine 0.043 g/L. The optimal amino acids addition allowed HA yield increased from 5.0 g/L of the control to 6.7 g/L in the validation experiments. Moreover, the modeling and optimization capacity of the RBF-QPSO approach was compared with that of response surface methodology (RSM). It was indicated that the RBF-QPSO approach gave a slightly better modeling and optimization result compared with RSM. The developed RBF-QPSO approach in this work may be helpful for the modeling and optimization of the other multivariable, nonlinear, time-variant bioprocesses.
Ahn, Junsik; Lee, Kyung Jin
2014-01-01
The purpose of this study is to optimize ELISA conditions to quantify the colorectal cancer antigen GA733 linked to the Fc antibody fragment fused to KDEL, an ER retention motif (GA733-FcK) expressed in transgenic plant. Variable conditions of capture antibody, blocking buffer, and detection antibody for ELISA were optimized with application of leaf extracts from transgenic plant expressing GA733-FcK. In detection antibody, anti-EpCAM/CD362 IgG recognizing the GA733 did not detect any GA733-FcK whereas anti-human Fc IgG recognizing the human Fc existed in plant leaf extracts. For blocking buffer conditions, 3% BSA buffer clearly blocked the plate, compared to the 5% skim-milk buffer. For capture antibody, monoclonal antibody (MAb) CO17-1A was applied to coat the plate with different amounts (1, 0.5, and 0.25 μg/well). Among the amounts of the capture antibody, 1 and 0.5 μg/well (capture antibody) showed similar absorbance, whereas 0.25 μg/well of the capture antibody showed significantly less absorbance. Taken together, the optimized conditions to quantify plant-derived GA733-FcK were 0.5 μg/well of MAb CO17-1A per well for the capture antibody, 3% BSA for blocking buffer, and anti-human Fc conjugated HRP. To confirm the optimized ELISA conditions, correlation analysis was conducted between the quantified amount of GA733-FcK in ELISA and its protein density values of different leaf samples in Western blot. The co-efficient value R2 between the ELISA quantified value and protein density was 0.85 (p<0.01), which indicates that the optimized ELISA conditions feasibly provides quantitative information of GA733-FcK expression in transgenic plant. PMID:24555929
Li, Dechun; Zhao, Shengzhi; Li, Guiqiu; Yang, Kejian
2007-08-20
A doubly Q-switched laser with both an acousto-optic (AO) modulator and a GaAs saturable absorber can obtain a more symmetric and shorter pulse with high pulse peak power, which has been experimentally proved. The key parameters of an optimally coupled doubly Q-switched laser with both an AO modulator and a GaAs saturable absorber are determined, and a group of general curves are generated for what we believe is the first time, when the single-photon absorption (SPA) and two-photon absorption (TPA) processes of GaAs are combined, and the Gaussian spatial distributions of the intracavity photon density and the initial population-inversion density as well as the influence of the AO Q-switch are considered. These key parameters include the optimal normalized coupling parameter, the optimal normalized GaAs saturable absorber parameters, and the normalized parameters of the AO Q-switch, which can maximize the output energy. Meanwhile, the corresponding normalized energy, the normalized peak power, and the normalized pulse width are given. The curves clearly show the dependence of the optimal key parameters on the parameters of the gain medium, the GaAs saturable absorber, the AO Q-switch, and the resonator. Sample calculations for a diode-pumped Nd3+:YVO4 laser with both an AO modulator and a GaAs saturable absorber are presented to demonstrate the use of the curves and the relevant formulas.
Modeling and Optimization Technique of a Chilled Water AHU Using Artificial Neural Network Methods
NASA Astrophysics Data System (ADS)
Talib, Rand Issa
Heating, ventilation, and air conditioning (HVAC) systems are widely used in buildings to provide occupants with conditioned air and acceptable indoor air quality. The chilled water system is one Heating, ventilation, and air conditioning systems are widely used in buildings to provide occupants with conditioned air and acceptable indoor air quality. The design of these systems constitutes a large impact on the energy usage and operating cost of buildings they serve. The ability to accurately predict the performance of these systems is integral to designing more energy efficient and sustainable building systems. In this thesis the modeling of a chilled water air handling units using Artificial Neural Networks model is proposed. The Artificial neural network model was built using four inputs (1) Chilled water temperature (CHWT), (2) Chilled water valve position (CWVLV), (3) Mixed air temperature (MAT), and (4) Supply air flow (SAF). The output of the model is to predict supply air temperature. Moreover, another model was constructed to predict the fan power as a function of the fan air flow and fan speed. The data that were collected from a real building in a span of three months were processed. The ANN model was trained using the measured data and different model structure were then tested with various time delay, feedback time, and number of neurons to determine the best structure. In addition, an optimization method is developed to automate the process of finding the best model structure that can produce the best accurate prediction against the actual data. The Coefficient of variances which was used to determine the error value was recorded to be as low as 1.22 for the best model structure. The obtained results validate the Artificial neural network model created as an accurate tool for predicting the performance of a chilled water air handling unit.
Optimization Of Shear Modes To Produce Enhanced Bandwidth In Ghz GaP Bragg Cells
NASA Astrophysics Data System (ADS)
Soos, J., I.; Rosemeier, R. G.; Rosenbaum, J.
1988-02-01
Applications of Gallium Phosphide (GaP) acousto-optic devices, at wavelengths from 570nm - 1.06um seem to be ideal for fiber optic modulators, scanners, deflectors, frequency shifters, Q-switches and mode lockers. One of the major applications are for RF spectrometers in early warning radar receivers and auto-correlators. Longitudinal GaP acousto-optic Bragg cells which have respectively operational frequencies in the range of 200 MHz - 3 GHz and diffraction efficiencies in the range of 120%/RF watt to 1%/RF watt have recently been fabricated. Comparatively, shear GaP devices which have operational frequencies in the range of 200 MHz to 2 GHz and diffraction efficiencies from 80%/RF watt to 7%/RF watt have also been constructed.
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.
Liu, Feng; Liu, Wenhui; Tian, Shuge
2014-09-01
A combination of an orthogonal L16(4)4 test design and a three-layer artificial neural network (ANN) model was applied to optimize polysaccharides from Althaea rosea seeds extracted by hot water method. The highest optimal experimental yield of A. rosea seed polysaccharides (ARSPs) of 59.85 mg/g was obtained using three extraction numbers, 113 min extraction time, 60.0% ethanol concentration, and 1:41 solid-liquid ratio. Under these optimized conditions, the ARSP experimental yield was very close to the predicted yield of 60.07 mg/g and was higher than the orthogonal test results (40.86 mg/g). Structural characterizations were conducted using physicochemical property and FTIR analysis. In addition, the study of ARSP antioxidant activity demonstrated that polysaccharides exhibited high superoxide dismutase activity, strong reducing power, and positive scavenging activity on superoxide anion, hydroxyl radical, 2,2-diphenyl-1-picrylhydrazyl, and reducing power. Our results indicated that ANNs were efficient quantitative tools for predicting the total ARSP content.
A noisy self-organizing neural network with bifurcation dynamics for combinatorial optimization.
Kwok, Terence; Smith, Kate A
2004-01-01
The self-organizing neural network (SONN) for solving general "0-1" combinatorial optimization problems (COPs) is studied in this paper, with the aim of overcoming existing limitations in convergence and solution quality. This is achieved by incorporating two main features: an efficient weight normalization process exhibiting bifurcation dynamics, and neurons with additive noise. The SONN is studied both theoretically and experimentally by using the N-queen problem as an example to demonstrate and explain the dependence of optimization performance on annealing schedules and other system parameters. An equilibrium model of the SONN with neuronal weight normalization is derived, which explains observed bands of high feasibility in the normalization parameter space in terms of bifurcation dynamics of the normalization process, and provides insights into the roles of different parameters in the optimization process. Under certain conditions, this dynamical systems view of the SONN reveals cascades of period-doubling bifurcations to chaos occurring in multidimensional space with the annealing temperature as the bifurcation parameter. A strange attractor in the two-dimensional (2-D) case is also presented. Furthermore, by adding random noise to the cost potentials of the network nodes, it is demonstrated that unwanted oscillations between symmetrical and "greedy" nodes can be sufficiently reduced, resulting in higher solution quality and feasibility.
Optimal control of distributed parameter systems using adaptive critic neural networks
NASA Astrophysics Data System (ADS)
Padhi, Radhakant
In this dissertation, two systematic optimal control synthesis techniques are presented for distributed parameter systems based on the adaptive critic neural networks. Following the philosophy of dynamic programming, this adaptive critic optimal control synthesis approach has many desirable features, viz. having a feedback form of the control, ability for on-line implementation, no need for approximating the nonlinear system dynamics, etc. More important, unlike the dynamic programming, it can accomplish these objectives without getting overwhelmed by the computational and storage requirements. First, an approximate dynamic programming based adaptive critic control synthesis formulation was carried out assuming an approximation of the system dynamics in a discrete form. A variety of example problems were solved using this proposed general approach. Next a different formulation is presented, which is capable of directly addressing the continuous form of system dynamics for control design. This was obtained following the methodology of Galerkin projection based weighted residual approximation using a set of orthogonal basis functions. The basis functions were designed by with the help of proper orthogonal decomposition, which leads to a very low-dimensional lumped parameter representation. The regulator problems of linear and nonlinear heat equations were revisited. Optimal controllers were synthesized first assuming a continuous controller and then a set of discrete controllers in the spatial domain. Another contribution of this study is the formulation of simplified adaptive critics for a large class of problems, which can be interpreted as a significant improvement of the existing adaptive critic technique.
Optimization of a hardware implementation for pulse coupled neural networks for image applications
NASA Astrophysics Data System (ADS)
Gimeno Sarciada, Jesús; Lamela Rivera, Horacio; Warde, Cardinal
2010-04-01
Pulse Coupled Neural Networks are a very useful tool for image processing and visual applications, since it has the advantages of being invariant to image changes as rotation, scale, or certain distortion. Among other characteristics, the PCNN changes a given image input into a temporal representation which can be easily later analyzed for pattern recognition. The structure of a PCNN though, makes it necessary to determine all of its parameters very carefully in order to function optimally, so that the responses to the kind of inputs it will be subjected are clearly discriminated allowing for an easy and fast post-processing yielding useful results. This tweaking of the system is a taxing process. In this paper we analyze and compare two methods for modeling PCNNs. A purely mathematical model is programmed and a similar circuital model is also designed. Both are then used to determine the optimal values of the several parameters of a PCNN: gain, threshold, time constants for feed-in and threshold and linking leading to an optimal design for image recognition. The results are compared for usefulness, accuracy and speed, as well as the performance and time requirements for fast and easy design, thus providing a tool for future ease of management of a PCNN for different tasks.
Simulation and optimization of current and lattice matching double-junction GaNAsP/Si solar cells
NASA Astrophysics Data System (ADS)
Nacer, S.; Aissat, A.
2016-01-01
This paper deals with theoretical investigation of the performance of current and lattice matched GaNxAsyP1-x-y/Si double-junction solar cells. The nitrogen and arsenic concentrations ensuring lattice matching to Si are determined. The band gap of GaNAsP is calculated using the band anti-crossing model. Calculations were performed under 1-sun AM1.5 using the one diode ideal model. Impact of minor carrier lifetime and surface recombination in the top sub-cell on the cell performances is analyzed. Optimum compositions of the top sub-cell have been identified (x = 4.5%, y = 11.5% and Eg = 1.68 eV). The simulation results predict, for the optimized GaNAsP/Si double-junction solar cell, a short circuit current Jsc = 20 mA/cm2, an open circuit voltage Voc = 1.95 V, and a conversion efficiency η = 37.5%.
Angular Rate Sensing with GyroWheel Using Genetic Algorithm Optimized Neural Networks.
Zhao, Yuyu; Zhao, Hui; Huo, Xin; Yao, Yu
2017-07-22
GyroWheel is an integrated device that can provide three-axis control torques and two-axis angular rate sensing for small spacecrafts. Large tilt angle of its rotor and de-tuned spin rate lead to a complex and non-linear dynamics as well as difficulties in measuring angular rates. In this paper, the problem of angular rate sensing with the GyroWheel is investigated. Firstly, a simplified rate sensing equation is introduced, and the error characteristics of the method are analyzed. According to the analysis results, a rate sensing principle based on torque balance theory is developed, and a practical way to estimate the angular rates within the whole operating range of GyroWheel is provided by using explicit genetic algorithm optimized neural networks. The angular rates can be determined by the measurable values of the GyroWheel (including tilt angles, spin rate and torque coil currents), the weights and the biases of the neural networks. Finally, the simulation results are presented to illustrate the effectiveness of the proposed angular rate sensing method with GyroWheel.
Angular Rate Sensing with GyroWheel Using Genetic Algorithm Optimized Neural Networks
Zhao, Yuyu; Zhao, Hui; Huo, Xin; Yao, Yu
2017-01-01
GyroWheel is an integrated device that can provide three-axis control torques and two-axis angular rate sensing for small spacecrafts. Large tilt angle of its rotor and de-tuned spin rate lead to a complex and non-linear dynamics as well as difficulties in measuring angular rates. In this paper, the problem of angular rate sensing with the GyroWheel is investigated. Firstly, a simplified rate sensing equation is introduced, and the error characteristics of the method are analyzed. According to the analysis results, a rate sensing principle based on torque balance theory is developed, and a practical way to estimate the angular rates within the whole operating range of GyroWheel is provided by using explicit genetic algorithm optimized neural networks. The angular rates can be determined by the measurable values of the GyroWheel (including tilt angles, spin rate and torque coil currents), the weights and the biases of the neural networks. Finally, the simulation results are presented to illustrate the effectiveness of the proposed angular rate sensing method with GyroWheel. PMID:28737684
NASA Astrophysics Data System (ADS)
Shan, Bonan; Wang, Jiang; Deng, Bin; Zhang, Zhen; Wei, Xile
2017-03-01
Assessment of the effective connectivity among different brain regions during seizure is a crucial problem in neuroscience today. As a consequence, a new model inversion framework of brain function imaging is introduced in this manuscript. This framework is based on approximating brain networks using a multi-coupled neural mass model (NMM). NMM describes the excitatory and inhibitory neural interactions, capturing the mechanisms involved in seizure initiation, evolution and termination. Particle swarm optimization method is used to estimate the effective connectivity variation (the parameters of NMM) and the epileptiform dynamics (the states of NMM) that cannot be directly measured using electrophysiological measurement alone. The estimated effective connectivity includes both the local connectivity parameters within a single region NMM and the remote connectivity parameters between multi-coupled NMMs. When the epileptiform activities are estimated, a proportional-integral controller outputs control signal so that the epileptiform spikes can be inhibited immediately. Numerical simulations are carried out to illustrate the effectiveness of the proposed framework. The framework and the results have a profound impact on the way we detect and treat epilepsy.
Casamento, Sonia; Kwok, Ben; Roux, Claude; Dawson, Michael; Doble, Philip
2003-09-01
The separation of 12 explosives by capillary electrophoresis was optimized with the aid of artificial neural networks (ANNs). The selectivity of the separation was manipulated by varying the concentration of sodium dodecyl sulfate (SDS) and the pH of the electrolyte, while maintaining the buffer concentration at 10 mM borate. The concentration of SDS and the electrolyte pH were used as input variables and the mobility of the explosives were used as output variables for the ANN. In total, eight experiments were performed based on a factorial design to train a variety of artificial neural network architectures. A further three experiments were required to train ANN architectures to adequately model the experimental space. A product resolution response surface was constructed based on the predicted mobilities of the best performing ANN. This response surface pointed to two optima; pH 9.0-9.1 and 60-65 mM SDS, and pH 8.4-8.6 and 50-60 mM SDS. Separation of all 12 explosives was achieved at the second optimum. The separation was further improved by changing the capillary to an extended cell detection window and reducing the diameter of the capillary from 75 microm to 50 microm. This provided a more efficient separation without compromising detection sensitivity.
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.
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.
Control chart pattern recognition using an optimized neural network and efficient features.
Ebrahimzadeh, Ata; Ranaee, Vahid
2010-07-01
Automatic recognition of abnormal patterns in control charts has seen increasing demands nowadays in manufacturing processes. This study investigates the design of an accurate system for control chart pattern (CCP) recognition from two aspects. First, an efficient system is introduced that includes two main modules: the feature extraction module and the classifier module. The feature extraction module uses the entropies of the wavelet packets. These are applied for the first time in this area. In the classifier module several neural networks, such as the multilayer perceptron and radial basis function, are investigated. Using an experimental study, we choose the best classifier in order to recognize the CCPs. Second, we propose a hybrid heuristic recognition system based on particle swarm optimization to improve the generalization performance of the classifier. The results obtained clearly confirm that further improvements in terms of recognition accuracy can be achieved by the proposed recognition system.
Missile Guidance Law Based on Robust Model Predictive Control Using Neural-Network Optimization.
Li, Zhijun; Xia, Yuanqing; Su, Chun-Yi; Deng, Jun; Fu, Jun; He, Wei
2015-08-01
In this brief, the utilization of robust model-based predictive control is investigated for the problem of missile interception. Treating the target acceleration as a bounded disturbance, novel guidance law using model predictive control is developed by incorporating missile inside constraints. The combined model predictive approach could be transformed as a constrained quadratic programming (QP) problem, which may be solved using a linear variational inequality-based primal-dual neural network over a finite receding horizon. Online solutions to multiple parametric QP problems are used so that constrained optimal control decisions can be made in real time. Simulation studies are conducted to illustrate the effectiveness and performance of the proposed guidance control law for missile interception.
Mackey-Glass noisy chaotic time series prediction by a swarm-optimized neural network
NASA Astrophysics Data System (ADS)
López-Caraballo, C. H.; Salfate, I.; Lazzús, J. A.; Rojas, P.; Rivera, M.; Palma-Chilla, L.
2016-05-01
In this study, an artificial neural network (ANN) based on particle swarm optimization (PSO) was developed for the time series prediction. The hybrid ANN+PSO algorithm was applied on Mackey-Glass noiseless chaotic time series in the short-term and long-term prediction. The performance prediction is evaluated and compared with similar work in the literature, particularly for the long-term forecast. Also, we present properties of the dynamical system via the study of chaotic behaviour obtained from the time series prediction. Then, this standard hybrid ANN+PSO algorithm was complemented with a Gaussian stochastic procedure (called stochastic hybrid ANN+PSO) in order to obtain a new estimator of the predictions that also allowed us compute uncertainties of predictions for noisy Mackey-Glass chaotic time series. We study the impact of noise for three cases with a white noise level (σ N ) contribution of 0.01, 0.05 and 0.1.
A unified framework for chaotic neural-network approaches to combinatorial optimization.
Kwok, T; Smith, K A
1999-01-01
As an attempt to provide an organized way to study the chaotic structures and their effects in solving combinatorial optimization with chaotic neural networks (CNN's), a unifying framework is proposed to serve as a basis where the existing CNN models can be placed and compared. The key of this proposed framework is the introduction of an extra energy term into the computational energy of the Hopfield model, which takes on different forms for different CNN models, and modifies the original Hopfield energy landscape in various manners. Three CNN models, namely the Chen and Aihara model with self-feedback chaotic simulated annealing (CSA), the Wang and Smith model with timestep CSA, and the chaotic noise model, are chosen as examples to show how they can be classified and compared within the proposed framework.
Predicting Tooth Surface Loss Using Genetic Algorithms-Optimized Artificial Neural Networks
Al Haidan, Ali; Abu-Hammad, Osama
2014-01-01
Our aim was to predict tooth surface loss in individuals without the need to conduct clinical examinations. Artificial neural networks (ANNs) were used to construct a mathematical model. Input data consisted of age, smoker status, type of tooth brush, brushing, and consumption of pickled food, fizzy drinks, orange, apple, lemon, and dried seeds. Output data were the sum of tooth surface loss scores for selected teeth. The optimized constructed ANN consisted of 2-layer network with 15 neurons in the first layer and one neuron in the second layer. The data of 46 subjects were used to build the model, while the data of 15 subjects were used to test the model. Accepting an error of ±5 scores for all chosen teeth, the accuracy of the network becomes more than 80%. In conclusion, this study shows that modeling tooth surface loss using ANNs is possible and can be achieved with a high degree of accuracy. PMID:25114713
Predicting tooth surface loss using genetic algorithms-optimized artificial neural networks.
Al Haidan, Ali; Abu-Hammad, Osama; Dar-Odeh, Najla
2014-01-01
Our aim was to predict tooth surface loss in individuals without the need to conduct clinical examinations. Artificial neural networks (ANNs) were used to construct a mathematical model. Input data consisted of age, smoker status, type of tooth brush, brushing, and consumption of pickled food, fizzy drinks, orange, apple, lemon, and dried seeds. Output data were the sum of tooth surface loss scores for selected teeth. The optimized constructed ANN consisted of 2-layer network with 15 neurons in the first layer and one neuron in the second layer. The data of 46 subjects were used to build the model, while the data of 15 subjects were used to test the model. Accepting an error of ±5 scores for all chosen teeth, the accuracy of the network becomes more than 80%. In conclusion, this study shows that modeling tooth surface loss using ANNs is possible and can be achieved with a high degree of accuracy.
Alvarado, Judith; Hanrahan, Grady; Nguyen, Huong T H; Gomez, Frank A
2012-09-01
This paper describes the use of a genetically tuned neural network platform to optimize the fluorescence realized upon binding 5-carboxyfluorescein-D-Ala-D-Ala-D-Ala (5-FAM-(D-Ala)(3) ) (1) to the antibiotic teicoplanin from Actinoplanes teichomyceticus electrostatically attached to a microfluidic channel originally modified with 3-aminopropyltriethoxysilane. Here, three parameters: (i) the length of time teicoplanin was in the microchannel; (ii) the length of time 1 was in the microchannel, thereby, in equilibrium with teicoplanin, and; (iii) the amount of time buffer was flushed through the microchannel to wash out any unbound 1 remaining in the channel, are examined at a constant concentration of 1, with neural network methodology applied to optimize fluorescence. Optimal neural structure provided a best fit model, both for the training set (r(2) = 0.985) and testing set (r(2) = 0.967) data. Simulated results were experimentally validated demonstrating efficiency of the neural network approach and proved superior to the use of multiple linear regression and neural networks using standard back propagation.
Songmuang, R; Giang, Le Thuy Thanh; Bleuse, J; Den Hertog, M; Niquet, Y M; Dang, Le Si; Mariette, H
2016-06-08
We present a set of experimental results showing a combination of various effects, that is, surface recombination velocity, surface charge traps, strain, and structural defects, that govern the carrier dynamics of self-catalyzed GaAs/AlGaAs core-shell nanowires (NWs) grown on a Si(111) substrate by molecular beam epitaxy. Time-resolved photoluminescence of NW ensemble and spatially resolved cathodoluminescence of single NWs reveal that emission intensity, decay time, and carrier diffusion length of the GaAs NW core strongly depend on the AlGaAs shell thickness but in a nonmonotonic fashion. Although 7 nm AlGaAs shell can efficiently suppress the surface recombination velocity of the GaAs NW core, the influence of the surface charge traps and the strain between the core and the shell that redshift the luminescence of the GaAs NW core remain observable in the whole range of the shell thickness. In addition, the band bending effect induced by the surface charge traps can alter the scattering of the excess carriers inside the GaAs NW core at the core/shell interface. If the AlGaAs shell thickness is larger than 50 nm, the luminescence efficiency of the GaAs NW cores deteriorates, ascribed to defect formation inside the AlGaAs shell evidenced by transmission electron microscopy.
Biefeld, R.M.; Baucom, K.C.; Kurtz, S.R.
1993-12-31
We have prepared InAsSb/InGaAs strained-layer superlattice (SLS) semiconductors by metal-organic chemical vapor deposition (MOCVD) under a variety of conditions. Presence of an InGaAsSb interface layer is indicated by x-ray diffraction patterns. Optimized growth conditions involved the use of low pressure, short purge times, and no reactant flow during the purges. MOCVD was used to prepare an optically pumped, single heterostructure InAsSb/InGaAs SLS/InPSb laser which emitted at 3.9 {mu}m with a maximum operating temperature of approximately 100 K.
Chen, Ho-Wen; Ning, Shu-Kuang; Yu, Ruey-Fang; Hung, Ming-Sung
2007-02-01
This paper applies artificial neural network (ANN) to model the observed effluent quality data. The ANN's structure, involving the number of hidden layer and node and their connection, is determined endogenously by resorting to the compromise of data cost minimization and prediction accuracy maximization. To obtain the best compromise possible, the model introduces an aspiration variable (micro) that represents the level of aspiration achieved in one objective and the conjugate of micro, (1 - micro), represents level of aspiration achieved in the other objective. Because a massive amount of calculation is required, the model applies genetic algorithm (GA) for its computational flexibility and capability to ensure global solution. Feasibility and practicality of the model is tested by a case study with a set of 150 daily observations on 17 operational variables and quality parameters at an industrial wastewater treatment plant (WTP) located in southern Taiwan. Of these 17 variables open to selection, only 6 variables, wastewater flow rate (Q), CN(-), SS, MLSS, pH and COD are selected by the model to achieve the maximum accuracy of prediction, 0.94, with a total cost of 5,950 NT$. By constraining budget availability, the variables included in the model are reduced in number, causing a concomitant reduction in prediction accuracy, that is, by varying micro (aspiration level of accuracy), a trajectory of cost and accuracy is generated. The calculation results a cost of 3,650 NT$ and 0.54 accuracy for the case with variables including flow rate, SCN(-) and SS in equalization basin; aeration tank hydraulic retention time (HRT) and percentage of returned sludge (R%) are selected for building the prediction model when the importance of required budget is equal to the accuracy of prediction model. In addition, when required cost for building ANN model is between 3,650 NT$ and 3,900 NT$, the marginal return of budget input is highest in the entire range of calculation.
Luitel, Bipul; Venayagamoorthy, Ganesh Kumar
2010-06-01
Training a single simultaneous recurrent neural network (SRN) to learn all outputs of a multiple-input-multiple-output (MIMO) system is a difficult problem. A new training algorithm developed from combined concepts of swarm intelligence and quantum principles is presented. The training algorithm is called particle swarm optimization with quantum infusion (PSO-QI). To improve the effectiveness of learning, a two-step learning approach is introduced in the training. The objective of the learning in the first step is to find the optimal set of weights in the SRN considering all output errors. In the second step, the objective is to maximize the learning of each output dynamics by fine tuning the respective SRN output weights. To demonstrate the effectiveness of the PSO-QI training algorithm and the two-step learning approach, two examples of an SRN learning MIMO systems are presented. The first example is learning a benchmark MIMO system and the second one is the design of a wide area monitoring system for a multimachine power system. From the results, it is observed that SRNs can effectively learn MIMO systems when trained using the PSO-QI algorithm and the two-step learning approach. Copyright 2009 Elsevier Ltd. All rights reserved.
Optimal waist-to-hip ratios in women activate neural reward centers in men.
Platek, Steven M; Singh, Devendra
2010-02-05
Secondary sexual characteristics convey information about reproductive potential. In the same way that facial symmetry and masculinity, and shoulder-to-hip ratio convey information about reproductive/genetic quality in males, waist-to-hip-ratio (WHR) is a phenotypic cue to fertility, fecundity, neurodevelopmental resources in offspring, and overall health, and is indicative of "good genes" in women. Here, using fMRI, we found that males show activation in brain reward centers in response to naked female bodies when surgically altered to express an optimal (approximately 0.7) WHR with redistributed body fat, but relatively unaffected body mass index (BMI). Relative to presurgical bodies, brain activation to postsurgical bodies was observed in bilateral orbital frontal cortex. While changes in BMI only revealed activation in visual brain substrates, changes in WHR revealed activation in the anterior cingulate cortex, an area associated with reward processing and decision-making. When regressing ratings of attractiveness on brain activation, we observed activation in forebrain substrates, notably the nucleus accumbens, a forebrain nucleus highly involved in reward processes. These findings suggest that an hourglass figure (i.e., an optimal WHR) activates brain centers that drive appetitive sociality/attention toward females that represent the highest-quality reproductive partners. This is the first description of a neural correlate implicating WHR as a putative honest biological signal of female reproductive viability and its effects on men's neurological processing.
Hayakawa, Yoshihiro; Nakajima, Koji
2010-02-01
We have already proposed the inverse function delayed (ID) model as a novel neuron model. The ID model has a negative resistance similar to Bonhoeffer-van der Pol (BVP) model and the network has an energy function similar to Hopfield model. The neural network having an energy can converge on a solution of the combinatorial optimization problem and the computation is in parallel and hence fast. However, the existence of local minima is a serious problem. The negative resistance of the ID model can make the network state free from such local minima by selective destabilization. Hence, we expect that it has a potential to overcome the local minimum problems. In computer simulations, we have already shown that the ID network can be free from local minima and that it converges on the optimal solutions. However, the theoretical analysis has not been presented yet. In this paper, we redefine three types of constraints for the particular problems, then we analytically estimate the appropriate network parameters giving the global minimum states only. Moreover, we demonstrate the validity of estimated network parameters by computer simulations.
Martarelli, D; Casettari, L; Shalaby, K S; Soliman, M E; Cespi, M; Bonacucina, G; Fagioli, L; Perinelli, D R; Lam, J K W; Palmieri, G F
2016-01-01
Efficacy of melatonin in treating sleep disorders has been demonstrated in numerous studies. Being with short half-life, melatonin needs to be formulated in extended-release tablets to prevent the fast drop of its plasma concentration. However, an attempt to mimic melatonin natural plasma levels during night time is challenging. In this work, Artificial Neural Networks (ANNs) were used to optimize melatonin release from hydrophilic polymer matrices. Twenty-seven different tablet formulations with different amounts of hydroxypropyl methylcellulose, xanthan gum and Carbopol®974P NF were prepared and subjected to drug release studies. Using dissolution test data as inputs for ANN designed by Visual Basic programming language, the ideal number of neurons in the hidden layer was determined trial and error methodology to guarantee the best performance of constructed ANN. Results showed that the ANN with nine neurons in the hidden layer had the best results. ANN was examined to check its predictability and then used to determine the best formula that can mimic the release of melatonin from a marketed brand using similarity fit factor. This work shows the possibility of using ANN to optimize the composition of prolonged-release melatonin tablets having dissolution profile desired.
Geometric-attributes-based segmentation of cortical bone slides using optimized neural networks.
Hage, Ilige S; Hamade, Ramsey F
2016-05-01
In cortical bone, solid (lamellar and interstitial) matrix occupies space left over by porous microfeatures such as Haversian canals, lacunae, and canaliculi-containing clusters. In this work, pulse-coupled neural networks (PCNN) were used to automatically distinguish the microfeatures present in histology slides of cortical bone. The networks' parameters were optimized using particle swarm optimization (PSO). When forming the fitness functions for the PSO, we considered the microfeatures' geometric attributes-namely, their size (based on measures of elliptical perimeter or area), shape (based on measures of compactness or the ratio of minor axis length to major axis length), and a two-way combination of these two geometric attributes. This hybrid PCNN-PSO method was further enhanced for pulse evaluation by combination with yet another method, adaptive threshold (AT), where the PCNN algorithm is repeated until the best threshold is found corresponding to the maximum variance between two segmented regions. Together, this framework of using PCNN-PSO-AT constitutes, we believe, a novel framework in biomedical imaging. Using this framework and extracting microfeatures from only one training image, we successfully extracted microfeatures from other test images. The high fidelity of all resultant segments was established using quantitative metrics such as precision, specificity, and Dice indices.
Optimizing the multiple quantum well thickness of an InGaN blue light emitting diode
NASA Astrophysics Data System (ADS)
Xu, Bing; Zhao, Jun Liang; Wang, Shu Guo; Dai, Hai Tao; Yu, Sheng-Fu; Lin, Ray-Ming; Chu, Fu-Chuan; Huang, Chou-Hsiung; Sun, Xiao Wei
2013-03-01
InGaN/GaN blue light emitting diodes with varied quantum well thickness from 2.4 nm to 3.6 nm are fabricated and characterized by atmosphere pressure metalorganic chemical vapor deposition (AP-MOCVD). Experimental results show that the exciton localization effect is enhanced from 21.76 to 23.48 by increasing the quantum well thickness from 2.4 nm to 2.7 nm. However, with the further increase of quantum well thickness, the exciton localization effect becomes weaker. Meanwhile, the peak wavelength of electroluminescence redshift with the increase of well thickness due to the larger quantum confined Stark effect (QCSE). In addition, the efficiency droop can be improved by increasing the well thickness.
Pendeo-Epitaxy Process Optimization of GaN for Novel Devices Applications
2008-04-01
uses the metal organic chemical vapor deposition (MOCVD) technique that commonly requires ammonia (NH3) and trimethyl gallium ( TMG ) as precursors...GaN are the growth temperature, the ammonia to TMG flow rate ratio (V:III ratio), the chamber pressure and the time to coalescence (Nam et al., 1998...1100, and (d) 1120 oC. (e) A schematic of the side wall crystallography at different growth temperatures. It is known that the ammonia to TMG
NASA Astrophysics Data System (ADS)
Maschio, Célio; José Schiozer, Denis
2015-01-01
In this article, a new optimization framework to reduce uncertainties in petroleum reservoir attributes using artificial intelligence techniques (neural network and genetic algorithm) is proposed. Instead of using the deterministic values of the reservoir properties, as in a conventional process, the parameters of the probability density function of each uncertain attribute are set as design variables in an optimization process using a genetic algorithm. The objective function (OF) is based on the misfit of a set of models, sampled from the probability density function, and a symmetry factor (which represents the distribution of curves around the history) is used as weight in the OF. Artificial neural networks are trained to represent the production curves of each well and the proxy models generated are used to evaluate the OF in the optimization process. The proposed method was applied to a reservoir with 16 uncertain attributes and promising results were obtained.
Sengupta, A.; Ranjan, P
2001-01-15
In this paper, we examine the possibility of using a multilayered feedforward neural network to extract tokamak plasma parameters from magnetic measurements as an improvement over the traditional methodology of function parametrization. It is also used to optimize the number and locations of the magnetic diagnostics designed for the tokamak. This work has been undertaken with the specific purpose of application of the neural network technique to the newly designed (and currently under fabrication) Superconducting Steady-State Tokamak-1 (SST-1). The magnetic measurements will be utilized to achieve real-time control of plasma shape, position, and some global profiles. A trained neural network is tested, and the results of parameter identification are compared with function parametrization. Both techniques appear well suited for the purpose, but a definite improvement with neural networks is observed. Although simulated measurements are used in this work, confidence regarding the network performance with actual experimental data is ensured by testing the network's noise tolerance with Gaussian noise of up to 10%. Finally, three possible methods of ranking the diagnostics in decreasing order of importance are suggested, and the neural network is used to optimize the number and locations of the magnetic sensors designed for SST-1. The results from the three methods are compared with one another and also with function parametrization. Magnetic probes within the plasma-facing side of the outboard limiter have been ranked high. Function parametrization and one of the neural network methods show a distinct tendency to favor the probes in the remote regions of the vacuum vessel, proving the importance of redundancy. Fault tolerance of the optimized network is tested. The results obtained should, in the long run, help in the decision regarding the final effective set of magnetic diagnostics to be used in SST-1 for reconstruction of the control parameters.
A neural network-based optimal spatial filter design method for motor imagery classification.
Yuksel, Ayhan; Olmez, Tamer
2015-01-01
In this study, a novel spatial filter design method is introduced. Spatial filtering is an important processing step for feature extraction in motor imagery-based brain-computer interfaces. This paper introduces a new motor imagery signal classification method combined with spatial filter optimization. We simultaneously train the spatial filter and the classifier using a neural network approach. The proposed spatial filter network (SFN) is composed of two layers: a spatial filtering layer and a classifier layer. These two layers are linked to each other with non-linear mapping functions. The proposed method addresses two shortcomings of the common spatial patterns (CSP) algorithm. First, CSP aims to maximize the between-classes variance while ignoring the minimization of within-classes variances. Consequently, the features obtained using the CSP method may have large within-classes variances. Second, the maximizing optimization function of CSP increases the classification accuracy indirectly because an independent classifier is used after the CSP method. With SFN, we aimed to maximize the between-classes variance while minimizing within-classes variances and simultaneously optimizing the spatial filter and the classifier. To classify motor imagery EEG signals, we modified the well-known feed-forward structure and derived forward and backward equations that correspond to the proposed structure. We tested our algorithm on simple toy data. Then, we compared the SFN with conventional CSP and its multi-class version, called one-versus-rest CSP, on two data sets from BCI competition III. The evaluation results demonstrate that SFN is a good alternative for classifying motor imagery EEG signals with increased classification accuracy.
Energy-efficient waveform shapes for neural stimulation revealed with genetic algorithm
Wongsarnpigoon, Amorn; Grill, Warren M.
2010-01-01
The energy efficiency of stimulation is an important consideration for battery-powered implantable stimulators. We used a genetic algorithm (GA) to determine the energy-optimal waveform shape for neural stimulation. The GA was coupled to a computational model of extracellular stimulation of a mammalian myelinated axon. As the GA progressed, waveforms became increasingly energy-efficient and converged upon an energy-optimal shape. The results of the GA were consistent across several trials, and resulting waveforms resembled truncated Gaussian curves. When constrained to monophasic cathodic waveforms, the GA produced waveforms that were symmetric about the peak, which occurred approximately during the middle of the pulse. However, when the cathodic waveforms were coupled to rectangular charge-balancing anodic pulses, the location and sharpness of the peak varied with the duration and timing (i.e., before or after cathodic phase) of the anodic phase. In a model of a population of mammalian axons and in vivo experiments on cat sciatic nerve, the GA-optimized waveforms were more energy-efficient and charge-efficient than several conventional waveform shapes used in neural stimulation. If used in implantable neural stimulators, GA-optimized waveforms could prolong battery life, thereby reducing the frequency of recharge intervals, the volume of implanted pulse generators, and the costs and risks of battery-replacement surgeries. PMID:20571186
Energy-efficient waveform shapes for neural stimulation revealed with a genetic algorithm
NASA Astrophysics Data System (ADS)
Wongsarnpigoon, Amorn; Grill, Warren M.
2010-08-01
The energy efficiency of stimulation is an important consideration for battery-powered implantable stimulators. We used a genetic algorithm (GA) to determine the energy-optimal waveform shape for neural stimulation. The GA was coupled to a computational model of extracellular stimulation of a mammalian myelinated axon. As the GA progressed, waveforms became increasingly energy efficient and converged upon an energy-optimal shape. The results of the GA were consistent across several trials, and resulting waveforms resembled truncated Gaussian curves. When constrained to monophasic cathodic waveforms, the GA produced waveforms that were symmetric about the peak, which occurred approximately during the middle of the pulse. However, when the cathodic waveforms were coupled to rectangular charge-balancing anodic pulses, the location and sharpness of the peak varied with the duration and timing (i.e., before or after the cathodic phase) of the anodic phase. In a model of a population of mammalian axons and in vivo experiments on a cat sciatic nerve, the GA-optimized waveforms were more energy efficient and charge efficient than several conventional waveform shapes used in neural stimulation. If used in implantable neural stimulators, GA-optimized waveforms could prolong battery life, thereby reducing the frequency of recharge intervals, the volume of implanted pulse generators, and the costs and risks of battery-replacement surgeries.
Hiyama, Takashi, Kouzuma, Shinichi; Imakubo, Tomofumi
1995-06-01
This paper presents an application of a neutral network for the identification of the optimal operating point of PV modules for the real time maximum power tracking control. The output power from the modules depends on the environmental factors such as insolation, cell temperature, and so on. Therefore, accurate identification of optimal operating point and real time continuous control are required to achieve the maximum output efficiency. The proposed neural network has a quite simple structure and provides a highly accurate identification of the optimal operating point and also a highly accurate estimation of the maximum power from the PV modules.
Evolutionary artificial neural networks by multi-dimensional particle swarm optimization.
Kiranyaz, Serkan; Ince, Turker; Yildirim, Alper; Gabbouj, Moncef
2009-12-01
In this paper, we propose a novel technique for the automatic design of Artificial Neural Networks (ANNs) by evolving to the optimal network configuration(s) within an architecture space. It is entirely based on a multi-dimensional Particle Swarm Optimization (MD PSO) technique, which re-forms the native structure of swarm particles in such a way that they can make inter-dimensional passes with a dedicated dimensional PSO process. Therefore, in a multidimensional search space where the optimum dimension is unknown, swarm particles can seek both positional and dimensional optima. This eventually removes the necessity of setting a fixed dimension a priori, which is a common drawback for the family of swarm optimizers. With the proper encoding of the network configurations and parameters into particles, MD PSO can then seek the positional optimum in the error space and the dimensional optimum in the architecture space. The optimum dimension converged at the end of a MD PSO process corresponds to a unique ANN configuration where the network parameters (connections, weights and biases) can then be resolved from the positional optimum reached on that dimension. In addition to this, the proposed technique generates a ranked list of network configurations, from the best to the worst. This is indeed a crucial piece of information, indicating what potential configurations can be alternatives to the best one, and which configurations should not be used at all for a particular problem. In this study, the architecture space is defined over feed-forward, fully-connected ANNs so as to use the conventional techniques such as back-propagation and some other evolutionary methods in this field. The proposed technique is applied over the most challenging synthetic problems to test its optimality on evolving networks and over the benchmark problems to test its generalization capability as well as to make comparative evaluations with the several competing techniques. The experimental
NASA Astrophysics Data System (ADS)
Haugan, H. J.; Brown, G. J.; Mahalingam, K.; Grazulis, L.
2015-05-01
In order to develop ternary antimonide-based superlattice (SL) materials for very long wavelength infrared (VLWIR) detection, systematic growth optimization studies were performed to produce high quality ternary materials. For the studies, a SL structure of 47.0 Å InAs/21.5 Å Ga0.75In0.25Sb was selected to create a very narrow band gap. Results indicate that an epitaxial process developed can produce a precisely controlled band gap around 50 meV, but the material quality of grown SL layers is particularly sensitive to growth defects formed during the growth process. Since Group III antisites and strain-induced dislocations are the dominant structural defects responsible for the low radiative efficiencies, our optimization strategies to eliminate these defects have focused on stabilizing III/V incorporation during surface reconstruction by manipulating the growth surface temperature and balancing the residual strain of the SLs by adjusting the As/Sb flux ratio. The optimized ternary SL materials exhibited an overall strong photoresponse over a wide wavelength range up to ∼15 μm that is important for developing VLWIR detectors. A quantitative analysis of the lattice strain, performed at the atomic scale by aberration corrected transmission electron microscopy, provided valuable information about the strain distribution at the interfaces that was important for optimizing the strain balancing process during SL layer growth.
Fan, Mingyi; Li, Tongjun; Hu, Jiwei; Cao, Rensheng; Wei, Xionghui; Shi, Xuedan; Ruan, Wenqian
2017-05-17
Reduced graphene oxide-supported nanoscale zero-valent iron (nZVI/rGO) composites were synthesized in the present study by chemical deposition method and were then characterized by various methods, such as Fourier-transform infrared spectroscopy (FTIR) and X-ray photoelectron spectroscopy (XPS). The nZVI/rGO composites prepared were utilized for Cd(II) removal from aqueous solutions in batch mode at different initial Cd(II) concentrations, initial pH values, contact times, and operating temperatures. Response surface methodology (RSM) and artificial neural network hybridized with genetic algorithm (ANN-GA) were used for modeling the removal efficiency of Cd(II) and optimizing the four removal process variables. The average values of prediction errors for the RSM and ANN-GA models were 6.47% and 1.08%. Although both models were proven to be reliable in terms of predicting the removal efficiency of Cd(II), the ANN-GA model was found to be more accurate than the RSM model. In addition, experimental data were fitted to the Langmuir, Freundlich, and Dubinin-Radushkevich (D-R) isotherms. It was found that the Cd(II) adsorption was best fitted to the Langmuir isotherm. Examination on thermodynamic parameters revealed that the removal process was spontaneous and exothermic in nature. Furthermore, the pseudo-second-order model can better describe the kinetics of Cd(II) removal with a good R² value than the pseudo-first-order model.
Zafar, Mohd; Van Vinh, N; Behera, Shishir Kumar; Park, Hung-Suck
2017-04-01
Organic matters (OMs) and their oxidization products often influence the fate and transport of heavy metals in the subsurface aqueous systems through interaction with the mineral surfaces. This study investigates the ethanol (EtOH)-mediated As(III) adsorption onto Zn-loaded pinecone (PC) biochar through batch experiments conducted under Box-Behnken design. The effect of EtOH on As(III) adsorption mechanism was quantitatively elucidated by fitting the experimental data using artificial neural network and quadratic modeling approaches. The quadratic model could describe the limiting nature of EtOH and pH on As(III) adsorption, whereas neural network revealed the stronger influence of EtOH (64.5%) followed by pH (20.75%) and As(III) concentration (14.75%) on the adsorption phenomena. Besides, the interaction among process variables indicated that EtOH enhances As(III) adsorption over a pH range of 2 to 7, possibly due to facilitation of ligand-metal(Zn) binding complexation mechanism. Eventually, hybrid response surface model-genetic algorithm (RSM-GA) approach predicted a better optimal solution than RSM, i.e., the adsorptive removal of As(III) (10.47μg/g) is facilitated at 30.22mg C/L of EtOH with initial As(III) concentration of 196.77μg/L at pH5.8. The implication of this investigation might help in understanding the application of biochar for removal of various As(III) species in the presence of OM. Copyright © 2016. Published by Elsevier B.V.
Optimization of ohmic contact for AlGaNGaN HEMT by introducing patterned etching in ohmic area
NASA Astrophysics Data System (ADS)
Wang, Chong; Zhao, Meng-Di; He, Yun-Long; Zheng, Xue-Feng; Wei, Xiao-Xiao; Mao, Wei; Ma, Xiao-Hua; Zhang, Jin-Cheng; Hao, Yue
2017-03-01
In this paper, the ohmic contact of AlGaNGaN HEMT was optimized by introducing patterned etching in ohmic area, and the conventional structure and whole etching structure were investigated for comparison. The contact resistance decreased from 0.46 Ω mm for conventional to 0.35 Ω mm and 0.18 Ω mm respectively for the whole etching and patterned etching structures. The current-voltage characteristics between the ohmic electrodes presented sharper slope, higher saturation current and lower knee voltage on patterned etching structures. After Cl2 plasma etching on ohmic area surface of AlGaN, the surface oxide layers and the pollutants were removed, therefore, the surface roughness of the ohmic metal reduced obviously, and the surface morphology improved. Meanwhile, the side area induced in patterned etching provided more extra contact area, which increased the tunneling current. The different apertures and the duty factor of patterned etching were investigated, and the results indicated that the quantity of side area produced in patterned etching dominated the reduction effect of ohmic contact resistance.
Forecasting the Dst index using a swarm-optimized neural network
NASA Astrophysics Data System (ADS)
Lazzús, J. A.; Vega, P.; Rojas, P.; Salfate, I.
2017-08-01
A hybrid technique that combines an artificial neural network with a particle swarm optimization (ANN+PSO) was used to forecast the disturbance storm time (Dst) index from 1 to 6 h ahead. Our ANN was optimized by PSO to update ANN weights and to predict the short-term Dst index using past values as input parameters. The database used contains 233,760 hourly data from 1 January 1990 to 31 August 2016, considering storms and quiet period, grouped into three data sets: learning set (with 116,880 hourly data points), validation set (with 58,440 data points), and testing set (with 58,440 data points). Several ANN topologies were studied, and the best architecture was determined by systematically adding neurons and evaluating the root-mean-square error (RMSE) and the correlation coefficient (R) during the training process. These results show that the hybrid algorithm is a powerful technique for forecasting the Dst index a short time in advance like t + 1 to t + 3, with RMSE from 3.5 nT to 7.5 nT, and R from 0.98 to 0.90. However, t + 4 to t + 6 predictions become slightly more uncertain, with RMSE from 8.8 nT to 10.9 nT, and R from 0.86 to 0.79. Additionally, an exhaustive analysis according to geomagnetic storm magnitude was conducted. In general, the results show that our hybrid algorithm can be correctly trained to forecast the Dst index with appropriate precision and that Dst past behavior significantly affects adequate training and predicting capabilities of the implemented ANN.
Vilim, R.B.; Wegerich, S.W.
1995-12-31
A neural network originally proposed by Szu for performing pattern recognition has been modified for use in a noisy manufacturing environment. Signals from the factory floor are frequently affine transformed and, as a consequence, a signal may not be properly aligned with respect to the input node that corresponds to the signal leading edge or with respect to the number of nodes representing the time varying part. Rater than translate and scale the presented signal, an operation which because of noise can be prone to numerical error since the signal is not smoothly varying, the network in this paper has the capability to analytically translate and scale its internal representation of the signal so that it overlays the presented signal. A response surface in the neighborhood of the stored reference signal is built during, training, and covers the range of translate and scale parameter values expected. A genetic algorithm is used to search over this hilly terrain to find the optimal values of these parameters so that the reference signal overlays the presented signal. The procedure is repeated over all hypothesized pattern classes with the best fit identifying the class.
Cohen, Michael X; Gulbinaite, Rasa
2017-02-15
Steady-state evoked potentials (SSEPs) are rhythmic brain responses to rhythmic sensory stimulation, and are often used to study perceptual and attentional processes. We present a data analysis method for maximizing the signal-to-noise ratio of the narrow-band steady-state response in the frequency and time-frequency domains. The method, termed rhythmic entrainment source separation (RESS), is based on denoising source separation approaches that take advantage of the simultaneous but differential projection of neural activity to multiple electrodes or sensors. Our approach is a combination and extension of existing multivariate source separation methods. We demonstrate that RESS performs well on both simulated and empirical data, and outperforms conventional SSEP analysis methods based on selecting electrodes with the strongest SSEP response, as well as several other linear spatial filters. We also discuss the potential confound of overfitting, whereby the filter captures noise in absence of a signal. Matlab scripts are available to replicate and extend our simulations and methods. We conclude with some practical advice for optimizing SSEP data analyses and interpreting the results.
NASA Astrophysics Data System (ADS)
Xing, Y. F.; Wang, Y. S.; Shi, L.; Guo, H.; Chen, H.
2016-01-01
According to the human perceptional characteristics, a method combined by the optimal wavelet-packet transform and artificial neural network, so-called OWPT-ANN model, for psychoacoustical recognition is presented. Comparisons of time-frequency analysis methods are performed, and an OWPT with 21 critical bands is designed for feature extraction of a sound, as is a three-layer back-propagation ANN for sound quality (SQ) recognition. Focusing on the loudness and sharpness, the OWPT-ANN model is applied on vehicle noises under different working conditions. Experimental verifications show that the OWPT can effectively transfer a sound into a time-varying energy pattern as that in the human auditory system. The errors of loudness and sharpness of vehicle noise from the OWPT-ANN are all less than 5%, which suggest a good accuracy of the OWPT-ANN model in SQ recognition. The proposed methodology might be regarded as a promising technique for signal processing in the human-hearing related fields in engineering.
Identification of optimal structural connectivity using functional connectivity and neural modeling.
Deco, Gustavo; McIntosh, Anthony R; Shen, Kelly; Hutchison, R Matthew; Menon, Ravi S; Everling, Stefan; Hagmann, Patric; Jirsa, Viktor K
2014-06-04
The complex network dynamics that arise from the interaction of the brain's structural and functional architectures give rise to mental function. Theoretical models demonstrate that the structure-function relation is maximal when the global network dynamics operate at a critical point of state transition. In the present work, we used a dynamic mean-field neural model to fit empirical structural connectivity (SC) and functional connectivity (FC) data acquired in humans and macaques and developed a new iterative-fitting algorithm to optimize the SC matrix based on the FC matrix. A dramatic improvement of the fitting of the matrices was obtained with the addition of a small number of anatomical links, particularly cross-hemispheric connections, and reweighting of existing connections. We suggest that the notion of a critical working point, where the structure-function interplay is maximal, may provide a new way to link behavior and cognition, and a new perspective to understand recovery of function in clinical conditions. Copyright © 2014 the authors 0270-6474/14/347910-07$15.00/0.
Denève, Sophie; Duhamel, Jean-René; Pouget, Alexandre
2007-05-23
Several behavioral experiments suggest that the nervous system uses an internal model of the dynamics of the body to implement a close approximation to a Kalman filter. This filter can be used to perform a variety of tasks nearly optimally, such as predicting the sensory consequence of motor action, integrating sensory and body posture signals, and computing motor commands. We propose that the neural implementation of this Kalman filter involves recurrent basis function networks with attractor dynamics, a kind of architecture that can be readily mapped onto cortical circuits. In such networks, the tuning curves to variables such as arm velocity are remarkably noninvariant in the sense that the amplitude and width of the tuning curves of a given neuron can vary greatly depending on other variables such as the position of the arm or the reliability of the sensory feedback. This property could explain some puzzling properties of tuning curves in the motor and premotor cortex, and it leads to several new predictions.
Growth optimization and optical properties of AlGaNAs alloys
NASA Astrophysics Data System (ADS)
Kolhatkar, Gitanjali; Boucherif, Abderraouf; Valdivia, Christopher E.; Wallace, Steven G.; Fafard, Simon; Aimez, Vincent; Arès, Richard
2014-04-01
The effect of Al on the surface morphology of chemical beam epitaxy grown AlGaNAs alloys is studied. Pits attributed to N clustering appearing on the dilute nitride surface become smaller, denser, and more uniformly distributed in the presence of Al. This reveals that the introduction of Al results in more homogenous N atoms spatial distribution. A growth temperature study reveals the formation of 3D structures at high temperature due to phase separation. The density of these structures decreases, while their diameter and height increase when the temperature is raised from 380 °C to 565 °C. At growth temperatures in the 380-420 °C range, the phase separation is suppressed and the growth mode is 2D. At 420 °C, the N incorporation is also maximized, making it the optimum temperature. The absorption coefficient and the bandgap of AlGaNAs alloys are extracted from transmittance measurement. A good agreement is obtained between the experimentally measured bandgap and the theoretical values calculated using the band anticrossing model. A bandgap as low as 1.22 eV was reached using Al and N concentrations of ˜15% and ˜3.4%, respectively.
Growth optimization and optical properties of AlGaNAs alloys
Kolhatkar, Gitanjali; Boucherif, Abderraouf; Aimez, Vincent; Arès, Richard; Valdivia, Christopher E.; Wallace, Steven G.; Fafard, Simon
2014-04-28
The effect of Al on the surface morphology of chemical beam epitaxy grown AlGaNAs alloys is studied. Pits attributed to N clustering appearing on the dilute nitride surface become smaller, denser, and more uniformly distributed in the presence of Al. This reveals that the introduction of Al results in more homogenous N atoms spatial distribution. A growth temperature study reveals the formation of 3D structures at high temperature due to phase separation. The density of these structures decreases, while their diameter and height increase when the temperature is raised from 380 °C to 565 °C. At growth temperatures in the 380–420 °C range, the phase separation is suppressed and the growth mode is 2D. At 420 °C, the N incorporation is also maximized, making it the optimum temperature. The absorption coefficient and the bandgap of AlGaNAs alloys are extracted from transmittance measurement. A good agreement is obtained between the experimentally measured bandgap and the theoretical values calculated using the band anticrossing model. A bandgap as low as 1.22 eV was reached using Al and N concentrations of ∼15% and ∼3.4%, respectively.
Raja, Muhammad Asif Zahoor; Khan, Junaid Ali; Ahmad, Siraj-ul-Islam; Qureshi, Ijaz Mansoor
2012-01-01
A methodology for solution of Painlevé equation-I is presented using computational intelligence technique based on neural networks and particle swarm optimization hybridized with active set algorithm. The mathematical model of the equation is developed with the help of linear combination of feed-forward artificial neural networks that define the unsupervised error of the model. This error is minimized subject to the availability of appropriate weights of the networks. The learning of the weights is carried out using particle swarm optimization algorithm used as a tool for viable global search method, hybridized with active set algorithm for rapid local convergence. The accuracy, convergence rate, and computational complexity of the scheme are analyzed based on large number of independents runs and their comprehensive statistical analysis. The comparative studies of the results obtained are made with MATHEMATICA solutions, as well as, with variational iteration method and homotopy perturbation method. PMID:22919371
Valdés, Julio J; Barton, Alan J
2007-05-01
A method for the construction of virtual reality spaces for visual data mining using multi-objective optimization with genetic algorithms on nonlinear discriminant (NDA) neural networks is presented. Two neural network layers (the output and the last hidden) are used for the construction of simultaneous solutions for: (i) a supervised classification of data patterns and (ii) an unsupervised similarity structure preservation between the original data matrix and its image in the new space. A set of spaces are constructed from selected solutions along the Pareto front. This strategy represents a conceptual improvement over spaces computed by single-objective optimization. In addition, genetic programming (in particular gene expression programming) is used for finding analytic representations of the complex mappings generating the spaces (a composition of NDA and orthogonal principal components). The presented approach is domain independent and is illustrated via application to the geophysical prospecting of caves.
Matsumoto, H.; Ohsawa, Y.; Takahashi, S.; Akiyama, T.; Hanaoka, H.; Ishiguro, O.
1997-03-01
A startup optimization control system for a gas and steam turbine combined cycle power plant is developed. The system can minimize startup time of the plant through cooperative fuzzy reasoning and a neural network autonomously adapting to varying process dynamics due to varying operational conditions, i.e. the ambient temperature and humidity. The operational conditions are taken into consideration by the neural network with a learning mechanism to optimize the schedule. The system is applied to a simulation for a plant with a three pressure staged reheat type 235.7 MW rated capacity, and the following points are seen: (1) the system can harmonize machines operations making good use of the operational margins, i.e. machine thermal stress and NOx emission; (2) startup time and energy loss are reduced by 35.6% and 26.3%, respectively, compared with the conventional off-line startup scheduling method.
Raja, Muhammad Asif Zahoor; Khan, Junaid Ali; Ahmad, Siraj-ul-Islam; Qureshi, Ijaz Mansoor
2012-01-01
A methodology for solution of Painlevé equation-I is presented using computational intelligence technique based on neural networks and particle swarm optimization hybridized with active set algorithm. The mathematical model of the equation is developed with the help of linear combination of feed-forward artificial neural networks that define the unsupervised error of the model. This error is minimized subject to the availability of appropriate weights of the networks. The learning of the weights is carried out using particle swarm optimization algorithm used as a tool for viable global search method, hybridized with active set algorithm for rapid local convergence. The accuracy, convergence rate, and computational complexity of the scheme are analyzed based on large number of independents runs and their comprehensive statistical analysis. The comparative studies of the results obtained are made with MATHEMATICA solutions, as well as, with variational iteration method and homotopy perturbation method.
Wang, Zhongqi; Yang, Bo; Kang, Yonggang; Yang, Yuan
2016-01-01
Fixture plays an important part in constraining excessive sheet metal part deformation at machining, assembly, and measuring stages during the whole manufacturing process. However, it is still a difficult and nontrivial task to design and optimize sheet metal fixture locating layout at present because there is always no direct and explicit expression describing sheet metal fixture locating layout and responding deformation. To that end, an RBF neural network prediction model is proposed in this paper to assist design and optimization of sheet metal fixture locating layout. The RBF neural network model is constructed by training data set selected by uniform sampling and finite element simulation analysis. Finally, a case study is conducted to verify the proposed method.
Optimization of Current Injection in AlGaInP Core-Shell Nanowire Light-Emitting Diodes.
Kivisaari, Pyry; Berg, Alexander; Karimi, Mohammad; Storm, Kristian; Limpert, Steven; Oksanen, Jani; Samuelson, Lars; Pettersson, Håkan; Borgström, Magnus T
2017-06-14
Core-shell nanowires offer great potential to enhance the efficiency of light-emitting diodes (LEDs) and expand the attainable wavelength range of LEDs over the whole visible spectrum. Additionally, nanowire (NW) LEDs can offer both improved light extraction and emission enhancement if the diameter of the wires is not larger than half the emission wavelength (λ/2). However, AlGaInP nanowire LEDs have so far failed to match the high efficiencies of traditional planar technologies, and the parameters limiting the efficiency remain unidentified. In this work, we show by experimental and theoretical studies that the small nanowire dimensions required for efficient light extraction and emission enhancement facilitate significant loss currents, which result in a low efficiency in radial NW LEDs in particular. To this end, we fabricate AlGaInP core-shell nanowire LEDs where the nanowire diameter is roughly equal to λ/2, and we find that both a large loss current and a large contact resistance are present in the samples. To investigate the significant loss current observed in the experiments in more detail, we carry out device simulations accounting for the full 3D nanowire geometry. According to the simulations, the low efficiency of radial AlGaInP nanowire LEDs can be explained by a substantial hole leakage to the outer barrier layer due to the small layer thicknesses and the close proximity of the shell contact. Using further simulations, we propose modifications to the epitaxial structure to eliminate such leakage currents and to increase the efficiency to near unity without sacrificing the λ/2 upper limit of the nanowire diameter. To gain a better insight of the device physics, we introduce an optical output measurement technique to estimate an ideality factor that is only dependent on the quasi-Fermi level separation in the LED. The results show ideality factors in the range of 1-2 around the maximum LED efficiency even in the presence of a very large voltage loss
NASA Astrophysics Data System (ADS)
Procházková, O.; Novotný, J.; Šrobár, F.
1992-05-01
Inclusion of the optimized composite waveguide concept in the InGaAsP/InP PBMR laser construction resulted in an improvement of the differential quantum efficiency value by more than ten per cent. Analysis of the kinetic equations for the carrier and photon populations was used to evaluate various contributions (radiative recombination, Auger processes, electron drift and parasitic leakage currents) to the threshold current in the optimized PBMR geometry.
Optimization of InGaAs/InAlAs Avalanche Photodiodes
NASA Astrophysics Data System (ADS)
Chen, Jun; Zhang, Zhengyu; Zhu, Min; Xu, Jintong; Li, Xiangyang
2017-01-01
In this paper, we report a two-dimensional (2D) simulation for InGaAs/InAlAs separate absorption, grading, charge, and multiplication avalanche photodiodes (SAGCM APDs) and study the effect of the charge layer and multiplication layer on the operating voltage ranges of APD. We find that with the increase of the thicknesses as well as the doping concentrations of the charge layer and the multiplication layer, the punchthrough voltage increases; with the increase of the doping concentrations of two layers and the thickness of the charge layer, the breakdown voltage decreases; with the increase of the thickness of the multiplication layer, the breakdown voltage first rapidly declines and then slightly rises.
Optimization of InGaAs/InAlAs Avalanche Photodiodes.
Chen, Jun; Zhang, Zhengyu; Zhu, Min; Xu, Jintong; Li, Xiangyang
2017-12-01
In this paper, we report a two-dimensional (2D) simulation for InGaAs/InAlAs separate absorption, grading, charge, and multiplication avalanche photodiodes (SAGCM APDs) and study the effect of the charge layer and multiplication layer on the operating voltage ranges of APD. We find that with the increase of the thicknesses as well as the doping concentrations of the charge layer and the multiplication layer, the punchthrough voltage increases; with the increase of the doping concentrations of two layers and the thickness of the charge layer, the breakdown voltage decreases; with the increase of the thickness of the multiplication layer, the breakdown voltage first rapidly declines and then slightly rises.
MOVPE GaN gas phase chemistry for reactor design and optimization
Safvi, S.A.; Thon, A.; Kuech, T.F.; Redwing, J.M.; Flynn, J.S.; Tischler, M.A.
1997-12-31
The results of gas phase decomposition studies are used to construct a chemistry model which is compared to data obtained from an experimental MOVPE reactor. A flow tube reactor is used to study gas phase reactions between trimethylgallium (TMG) and ammonia at high temperatures, characteristic to the metalorganic vapor phase epitaxy (MOVPE) of GaN. Experiments were performed to determine the effect of the mixing of the Group III precursors and Group V precursors on the growth rate, growth uniformity and film properties. Growth rates are predicted for simple reaction mechanisms and compared to those obtained experimentally. Quantification of the loss of reacting species due to oligomerization is made based on experimentally observed growth rates. The model is used to obtain trends in growth rate and uniformity with the purpose of moving towards better operating conditions.
Witek-Krowiak, Anna; Chojnacka, Katarzyna; Podstawczyk, Daria; Dawiec, Anna; Pokomeda, Karol
2014-05-01
A review on the application of response surface methodology (RSM) and artificial neural networks (ANN) in biosorption modelling and optimization is presented. The theoretical background of the discussed methods with the application procedure is explained. The paper describes most frequently used experimental designs, concerning their limitations and typical applications. The paper also presents ways to determine the accuracy and the significance of model fitting for both methodologies described herein. Furthermore, recent references on biosorption modelling and optimization with the use of RSM and the ANN approach are shown. Special attention was paid to the selection of factors and responses, as well as to statistical analysis of the modelling results.
Liu, Derong; Wang, Ding; Wang, Fei-Yue; Li, Hongliang; Yang, Xiong
2014-12-01
In this paper, the infinite horizon optimal robust guaranteed cost control of continuous-time uncertain nonlinear systems is investigated using neural-network-based online solution of Hamilton-Jacobi-Bellman (HJB) equation. By establishing an appropriate bounded function and defining a modified cost function, the optimal robust guaranteed cost control problem is transformed into an optimal control problem. It can be observed that the optimal cost function of the nominal system is nothing but the optimal guaranteed cost of the original uncertain system. A critic neural network is constructed to facilitate the solution of the modified HJB equation corresponding to the nominal system. More importantly, an additional stabilizing term is introduced for helping to verify the stability, which reinforces the updating process of the weight vector and reduces the requirement of an initial stabilizing control. The uniform ultimate boundedness of the closed-loop system is analyzed by using the Lyapunov approach as well. Two simulation examples are provided to verify the effectiveness of the present control approach.
Zhang, Peng; Liu, Keping; Zhao, Bo; Li, Yuanchun
2015-01-01
Optimal guidance is essential for the soft landing task. However, due to its high computational complexities, it is hardly applied to the autonomous guidance. In this paper, a computationally inexpensive optimal guidance algorithm based on the radial basis function neural network (RBFNN) is proposed. The optimization problem of the trajectory for soft landing on asteroids is formulated and transformed into a two-point boundary value problem (TPBVP). Combining the database of initial states with the relative initial co-states, an RBFNN is trained offline. The optimal trajectory of the soft landing is determined rapidly by applying the trained network in the online guidance. The Monte Carlo simulations of soft landing on the Eros433 are performed to demonstrate the effectiveness of the proposed guidance algorithm. PMID:26367382
Zhang, Peng; Liu, Keping; Zhao, Bo; Li, Yuanchun
2015-01-01
Optimal guidance is essential for the soft landing task. However, due to its high computational complexities, it is hardly applied to the autonomous guidance. In this paper, a computationally inexpensive optimal guidance algorithm based on the radial basis function neural network (RBFNN) is proposed. The optimization problem of the trajectory for soft landing on asteroids is formulated and transformed into a two-point boundary value problem (TPBVP). Combining the database of initial states with the relative initial co-states, an RBFNN is trained offline. The optimal trajectory of the soft landing is determined rapidly by applying the trained network in the online guidance. The Monte Carlo simulations of soft landing on the Eros433 are performed to demonstrate the effectiveness of the proposed guidance algorithm.
A Neural Network Solution for Fixed-Final Time Optimal Control of Nonlinear Systems
2006-06-01
nonlinear systems. The method is based on Kronecker matrix methods along with neural network approximation over a compact set to solve a time-varying...Hamilton-Jacobi-Bellman equation. The result is a neural network feedback controller that has time-varying coefficients found by a priori offline tuning
Optimal multiple-information integration inherent in a ring neural network
NASA Astrophysics Data System (ADS)
Takiyama, Ken
2017-02-01
Although several behavioral experiments have suggested that our neural system integrates multiple sources of information based on the certainty of each type of information in the manner of maximum-likelihood estimation, it is unclear how the maximum-likelihood estimation is implemented in our neural system. Here, I investigate the relationship between maximum-likelihood estimation and a widely used ring-type neural network model that is used as a model of visual, motor, or prefrontal cortices. Without any approximation or ansatz, I analytically demonstrate that the equilibrium of an order parameter in the neural network model exactly corresponds to the maximum-likelihood estimation when the strength of the symmetrical recurrent synaptic connectivity within a neural population is appropriately stronger than that of asymmetrical connectivity, that of local and external inputs, and that of symmetrical or asymmetrical connectivity between different neural populations. In this case, strengths of local and external inputs or those of symmetrical connectivity between different neural populations exactly correspond to the input certainty in maximum-likelihood estimation. Thus, my analysis suggests appropriately strong symmetrical recurrent connectivity as a possible candidate for implementing the maximum-likelihood estimation within our neural system.
Cosentino, Stefano; Gaudrain, Etienne; Deeks, John M; Carlyon, Robert P
2016-04-01
Electrically evoked compound action potentials (ECAPs) have been employed as a measure of neural activation evoked by cochlear implant (CI) stimulation. A forward-masking procedure is commonly used to reduce stimulus artefacts. This method estimates the joint neural activation produced by two electrodes-one acting as probe and the other as masker; as such, the measured ECAPs depend on the activation patterns produced by both. We describe an approach--termed panoramic ECAP ("PECAP")--that allows reconstruction of the underlying neural activation pattern of individual channels from ECAP amplitudes. The proposed approach combines two constrained nonlinear optimization stages. PECAP was validated against simulated and physiological data from CI users. The physiological data consisted of ECAPs measured from four users of Cochlear devices. For each subject, an 18 ×18 ECAP amplitude matrix was measured using a forward-masking method. The results from computer simulations indicate that our approach can reliably estimate the underlying activation patterns from ECAP amplitudes even for instances of neural "dead regions" or cross-turn stimulation. The operating signal-to-noise ratio (SNR) for the proposed algorithm was 5 dB or higher, which matched well the SNR measured from human physiological data. Human ECAPs were fitted with our procedure to determine neural activation patterns. PECAP can be used to identify undesirable features of the neural activation pattern of individual CI users. Our approach may have clinical application as an objective measure of electrode-to-neuron interface and may be used to devise ad hoc stimulation strategies.
Optimal Poly(l-lysine) Grafting Density in Hydrogels for Promoting Neural Progenitor Cell Functions
Cai, Lei; Lu, Jie; Sheen, Volney; Wang, Shanfeng
2012-01-01
Recently we have developed a photo-polymerizable poly(l-lysine) (PLL) that can be covalently incorporated into poly(ethylene glycol) diacrylate (PEGDA) hydrogels to improve their bioactivity by providing positive charges. To explore the potential of these PLL-grafted PEGDA hydrogels as a cell delivery vehicle and luminal filler in nerve guidance conduits for peripheral and central nerve regeneration, we varied the amount of pendent PLL chains in the hydrogels by photo-crosslinking PEGDA with weight compositions of PLL (ϕPLL) of 0, 1%, 2%, 3%, and 5%. We further investigated the effect of PLL grafting density on E14 mouse neural progenitor cell (NPC) behavior including cell viability, attachment, proliferation, differentiation, and gene expression. The amount of actually grafted PLL and charge densities were characterized, showing a proportional increase with the feed composition ϕPLL. NPC viability in 3D hydrogels was significantly improved in a PLL grafting density-dependent manner at days 7 and 14 post-encapsulation. Similarly, NPC attachment and proliferation were promoted on the PLL-grafted hydrogels with increasing ϕPLL up to 2%. More intriguingly, NPC lineage commitment was dramatically altered by the amount of grafted PLL chains in the hydrogels. NPC differentiation demonstrated a parabolic or non-monotonic dependence on ϕPLL, resulting in cells mostly differentiated toward mature neurons with extensive neurite formation and astrocytes rather than oligodendrocytes on the PLL-grafted hydrogels with ϕPLL of 2%, whereas the neutral hydrogels and PLL-grafted hydrogels with higher ϕPLL of 5% support NPC differentiation less. Gene expression of lineage markers further illustrated this trend, indicating that PLL-grafted hydrogels with an optimal ϕPLL of 2% could be a promising cell carrier that promoted NPC functions for treatment of nerve injuries. PMID:22533450
Optimization of time for neural stem cells transplantation for brain stroke in rats
Ziaee, Seyyed Mohyeddin; Tabeshmehr, Parisa; Haider, Khawaja Husnain; Farrokhi, Majidreza; Shariat, Abdolhamid; Amiri, Atena
2017-01-01
Background Despite encouraging data in terms of neurological outcome, stem cell based therapy for ischemic stroke in experimental models and human patients is still hampered by multiple as yet un-optimized variables, i.e., time of intervention, that significantly influence the prognosis. The aim of the present study was to delineate the optimum time for neural stem cells (NSCs) transplantation after ischemic stroke. Methods The NSCs were isolated from 14 days embryo rat ganglion eminence and were cultured in NSA medium (neurobasal medium, 2% B27, 1% N2, bFGF 10 ng/mL, EGF 20 ng/mL and 1% pen/strep). The cells were characterized for tri-lineage differentiation by immunocytochemistry for tubulin-III, Olig2 and GFAP expression for neurons, oligodendrocytes and astrocyte respectively. The NSCs at passage 3 were injected intraventricularly in a rodent model of middle-cerebral artery occlusion (MCAO) on stipulated time points of 1 & 12 h, and 1, 3, 5 and 7 days after ischemic stroke. The animals were euthanized on day 28 after their respective treatment. Results dUTP nick end labeling (TUNEL) assay and Caspase assay showed significantly reduced number of apoptotic cells on day 3 treated animals as compared to the other treatment groups of animals. The neurological outcome showed that the group which received NSCs 3 days after brain ischemia had the best neurological performance. Conclusions The optimum time for NSCs transplantation was day 3 after ischemic stroke in terms of attenuation of ischemic zone expansion and better preserved neurological performance. PMID:28529944
Optimal design of neural networks for land-cover classification from multispectral imagery
NASA Astrophysics Data System (ADS)
Silvan-Cardenas, Jose L.
2004-02-01
It has long been shown the effectiveness of artificial neural networks to solve highly non-linear problems such as land-cover classification based on multispectral imagery. However, due to the large amount of data that is processed within this kind of applications, it is desirable to design networks with the lowest number of neurons that are capable to separate all of the given classes. At present, there are several methods intended to determine this optimal network. Most of them involve adjoining or pruning hidden neurons followed by further training in iterative fashion, which is generally a very slow process. As an alternative, the approach described in this paper is based on the computation of centroids of relevant clusters for each class samples through the well known clustering method ISODATA. A proper tessellation of the ISODATA centroids allows first the determination of the minimum number of neurons in the first hidden layer that are required to effectively separate all of the classes; and secondly, to compute weight and bias parameters for such neurons. Then, the minimum network required to perform the logic function that combines the halfspaces generated by the first layer into class-discriminant surfaces is determined via a logic function reduction method. This approach is much faster than that of current methods because it allows to determine the optimum network size and compute weight and bias parameters without further iterative adjustments. The procedure was tested with landsat 7 Enhanced Thematic Mapper Plus (ETM+) data. Results indicated that (1) the network exhibits good generalization behavior and (2) classification accuracies do not depend on the class boundary complexity but only on the class overlapping extent.
Optimization of time for neural stem cells transplantation for brain stroke in rats.
Ziaee, Seyyed Mohyeddin; Tabeshmehr, Parisa; Haider, Khawaja Husnain; Farrokhi, Majidreza; Shariat, Abdolhamid; Amiri, Atena; Hosseini, Seyed Mojtaba
2017-01-01
Despite encouraging data in terms of neurological outcome, stem cell based therapy for ischemic stroke in experimental models and human patients is still hampered by multiple as yet un-optimized variables, i.e., time of intervention, that significantly influence the prognosis. The aim of the present study was to delineate the optimum time for neural stem cells (NSCs) transplantation after ischemic stroke. The NSCs were isolated from 14 days embryo rat ganglion eminence and were cultured in NSA medium (neurobasal medium, 2% B27, 1% N2, bFGF 10 ng/mL, EGF 20 ng/mL and 1% pen/strep). The cells were characterized for tri-lineage differentiation by immunocytochemistry for tubulin-III, Olig2 and GFAP expression for neurons, oligodendrocytes and astrocyte respectively. The NSCs at passage 3 were injected intraventricularly in a rodent model of middle-cerebral artery occlusion (MCAO) on stipulated time points of 1 & 12 h, and 1, 3, 5 and 7 days after ischemic stroke. The animals were euthanized on day 28 after their respective treatment. dUTP nick end labeling (TUNEL) assay and Caspase assay showed significantly reduced number of apoptotic cells on day 3 treated animals as compared to the other treatment groups of animals. The neurological outcome showed that the group which received NSCs 3 days after brain ischemia had the best neurological performance. The optimum time for NSCs transplantation was day 3 after ischemic stroke in terms of attenuation of ischemic zone expansion and better preserved neurological performance.
NASA Astrophysics Data System (ADS)
Hayatbini, N.; Faridzad, M.; Yang, T.; Akbari Asanjan, A.; Gao, X.; Sorooshian, S.
2016-12-01
The Artificial Neural Networks (ANNs) are useful in many fields, including water resources engineering and management. However, due to the non-linear and chaotic characteristics associated with natural processes and human decision making, the use of ANNs in real-world applications is still limited, and its performance needs to be further improved for a broader practical use. The commonly used Back-Propagation (BP) scheme and gradient-based optimization in training the ANNs have already found to be problematic in some cases. The BP scheme and gradient-based optimization methods are associated with the risk of premature convergence, stuck in local optimums, and the searching is highly dependent on initial conditions. Therefore, as an alternative to BP and gradient-based searching scheme, we propose an effective and efficient global searching method, termed the Shuffled Complex Evolutionary Global optimization algorithm with Principal Component Analysis (SP-UCI), to train the ANN connectivity weights. Large number of real-world datasets are tested with the SP-UCI-based ANN, as well as various popular Evolutionary Algorithms (EAs)-enhanced ANNs, i.e., Particle Swarm Optimization (PSO)-, Genetic Algorithm (GA)-, Simulated Annealing (SA)-, and Differential Evolution (DE)-enhanced ANNs. Results show that SP-UCI-enhanced ANN is generally superior over other EA-enhanced ANNs with regard to the convergence and computational performance. In addition, we carried out a case study for hydropower scheduling in the Trinity Lake in the western U.S. In this case study, multiple climate indices are used as predictors for the SP-UCI-enhanced ANN. The reservoir inflows and hydropower releases are predicted up to sub-seasonal to seasonal scale. Results show that SP-UCI-enhanced ANN is able to achieve better statistics than other EAs-based ANN, which implies the usefulness and powerfulness of proposed SP-UCI-enhanced ANN for reservoir operation, water resources engineering and management
Fu, Xingang; Li, Shuhui; Fairbank, Michael; Wunsch, Donald C; Alonso, Eduardo
2015-09-01
This paper investigates how to train a recurrent neural network (RNN) using the Levenberg-Marquardt (LM) algorithm as well as how to implement optimal control of a grid-connected converter (GCC) using an RNN. To successfully and efficiently train an RNN using the LM algorithm, a new forward accumulation through time (FATT) algorithm is proposed to calculate the Jacobian matrix required by the LM algorithm. This paper explores how to incorporate FATT into the LM algorithm. The results show that the combination of the LM and FATT algorithms trains RNNs better than the conventional backpropagation through time algorithm. This paper presents an analytical study on the optimal control of GCCs, including theoretically ideal optimal and suboptimal controllers. To overcome the inapplicability of the optimal GCC controller under practical conditions, a new RNN controller with an improved input structure is proposed to approximate the ideal optimal controller. The performance of an ideal optimal controller and a well-trained RNN controller was compared in close to real-life power converter switching environments, demonstrating that the proposed RNN controller can achieve close to ideal optimal control performance even under low sampling rate conditions. The excellent performance of the proposed RNN controller under challenging and distorted system conditions further indicates the feasibility of using an RNN to approximate optimal control in practical applications.
Lake, Spencer T; Greene, Kirsten L; Westphalen, Antonio C; Behr, Spencer C; Zagoria, Ronald; Small, Eric J; Carroll, Peter R; Hope, Thomas A
2017-09-19
PET/MRI can be used for the detection of disease in biochemical recurrence (BCR) patients imaged with (68)Ga-PSMA-11 PET. This study was designed to determine the optimal MRI sequences to localize positive findings on (68)Ga-PSMA-11 PET of patients with BCR after definitive therapy. Fifty-five consecutive prostate cancer patients with BCR imaged with (68)Ga-PSMA-11 3.0T PET/MRI were retrospectively analyzed. Mean PSA was 7.9 ± 12.9 ng/ml, and mean PSA doubling time was 7.1 ± 6.6 months. Detection rates of anatomic correlates for prostate-specific membrane antigen (PSMA)-positive foci were evaluated on small field of view (FOV) T2, T1 post-contrast, and diffusion-weighted images. For prostate bed recurrences, the detection rate of dynamic contrast-enhanced (DCE) imaging for PSMA-positive foci was evaluated. Finally, the detection sensitivity for PSMA-avid foci on 3- and 8-min PET acquisitions was compared. PSMA-positive foci were detected in 89.1% (49/55) of patients evaluated. Small FOV T2 performed best for lymph nodes and detected correlates for all PSMA-avid lymph nodes. DCE imaging performed the best for suspected prostate bed recurrence, detecting correlates for 87.5% (14/16) of PSMA-positive prostate bed foci. The 8-min PET acquisition performed better than the 3-min acquisition for lymph nodes smaller than 1 cm, detecting 100% (57/57) of lymph nodes less than 1 cm, compared to 78.9% (45/57) for the 3-min acquisition. PSMA PET/MRI performed well for the detection of sites of suspected recurrent disease in patients with BCR. Of the MRI sequences obtained for localization, small FOV T2 images detected the greatest proportion of PSMA-positive abdominopelvic lymph nodes and DCE imaging detected the greatest proportion of PSMA-positive prostate bed foci. The 8-min PET acquisition was superior to the 3 min acquisition for detection of small lymph nodes.
Performance-optimized hierarchical models predict neural responses in higher visual cortex
Yamins, Daniel L. K.; Hong, Ha; Cadieu, Charles F.; Solomon, Ethan A.; Seibert, Darren; DiCarlo, James J.
2014-01-01
The ventral visual stream underlies key human visual object recognition abilities. However, neural encoding in the higher areas of the ventral stream remains poorly understood. Here, we describe a modeling approach that yields a quantitatively accurate model of inferior temporal (IT) cortex, the highest ventral cortical area. Using high-throughput computational techniques, we discovered that, within a class of biologically plausible hierarchical neural network models, there is a strong correlation between a model’s categorization performance and its ability to predict individual IT neural unit response data. To pursue this idea, we then identified a high-performing neural network that matches human performance on a range of recognition tasks. Critically, even though we did not constrain this model to match neural data, its top output layer turns out to be highly predictive of IT spiking responses to complex naturalistic images at both the single site and population levels. Moreover, the model’s intermediate layers are highly predictive of neural responses in the V4 cortex, a midlevel visual area that provides the dominant cortical input to IT. These results show that performance optimization—applied in a biologically appropriate model class—can be used to build quantitative predictive models of neural processing. PMID:24812127
NASA Astrophysics Data System (ADS)
Kamaruddin, Saadi Bin Ahmad; Marponga Tolos, Siti; Hee, Pah Chin; Ghani, Nor Azura Md; Ramli, Norazan Mohamed; Nasir, Noorhamizah Binti Mohamed; Ksm Kader, Babul Salam Bin; Saiful Huq, Mohammad
2017-03-01
Neural framework has for quite a while been known for its ability to handle a complex nonlinear system without a logical model and can learn refined nonlinear associations gives. Theoretically, the most surely understood computation to set up the framework is the backpropagation (BP) count which relies on upon the minimization of the mean square error (MSE). However, this algorithm is not totally efficient in the presence of outliers which usually exist in dynamic data. This paper exhibits the modelling of quadriceps muscle model by utilizing counterfeit smart procedures named consolidated backpropagation neural network nonlinear autoregressive (BPNN-NAR) and backpropagation neural network nonlinear autoregressive moving average (BPNN-NARMA) models in view of utilitarian electrical incitement (FES). We adapted particle swarm optimization (PSO) approach to enhance the performance of backpropagation algorithm. In this research, a progression of tests utilizing FES was led. The information that is gotten is utilized to build up the quadriceps muscle model. 934 preparing information, 200 testing and 200 approval information set are utilized as a part of the improvement of muscle model. It was found that both BPNN-NAR and BPNN-NARMA performed well in modelling this type of data. As a conclusion, the neural network time series models performed reasonably efficient for non-linear modelling such as active properties of the quadriceps muscle with one input, namely output namely muscle force.
NASA Astrophysics Data System (ADS)
Lahmiri, Salim
2016-02-01
Multiresolution analysis techniques including continuous wavelet transform, empirical mode decomposition, and variational mode decomposition are tested in the context of interest rate next-day variation prediction. In particular, multiresolution analysis techniques are used to decompose interest rate actual variation and feedforward neural network for training and prediction. Particle swarm optimization technique is adopted to optimize its initial weights. For comparison purpose, autoregressive moving average model, random walk process and the naive model are used as main reference models. In order to show the feasibility of the presented hybrid models that combine multiresolution analysis techniques and feedforward neural network optimized by particle swarm optimization, we used a set of six illustrative interest rates; including Moody's seasoned Aaa corporate bond yield, Moody's seasoned Baa corporate bond yield, 3-Month, 6-Month and 1-Year treasury bills, and effective federal fund rate. The forecasting results show that all multiresolution-based prediction systems outperform the conventional reference models on the criteria of mean absolute error, mean absolute deviation, and root mean-squared error. Therefore, it is advantageous to adopt hybrid multiresolution techniques and soft computing models to forecast interest rate daily variations as they provide good forecasting performance.
NASA Astrophysics Data System (ADS)
Mondal, Praloy; Das, Debajyoti
2017-07-01
Technologically appropriate device friendly ZnO:Ga films have been prepared at a low growth temperature (100 °C) by changing the RF power (P) applied to the magnetron plasma. Structurally preferred c-axis orientation of the ZnO:Ga network has been attained with I<002>/I<103> > 5. The c-axis oriented grains of wurtzite ZnO:Ga grows geometrically and settles in tangentially, providing favorable conduction path for stacked layer devices. Nano-sheet like structures produced at the surface are interconnected and provide conducting path across the surface; however, those accommodate a lot of pores in between that help better light trapping and reduce the reflection loss. The optimized ZnO:Ga thin film prepared at RF power of 200 W has <002> oriented grains of average size ∼10 nm and exhibits a very high conductivity ∼200 S cm-1 and elevated transmission (∼93% at 500 nm) in the visible range. The optimized ZnO:Ga film has been used as the transparent conducting oxide (TCO) window layer of RF-PECVD grown silicon thin film solar cells in glass/TCO/p-i-n-Si/Al configuration. The characteristics of identically prepared p-i-n-Si solar cells are compared by replacing presently developed ZnO:Ga TCO with the best quality U-type SnO2 coated Asahi glass substrates. The ZnO:Ga coated glass substrate offers a higher open circuit voltage (VOC) and the higher fill factor (FF). The ZnO:Ga film being more stable in hydrogen plasma than its SnO2 counterpart, maintains a high transparency to the solar radiation and improves the VOC, while reduced diffusion of Zn across the p-layer creates less defects at the p-i interface in Si:H cells and thereby, increases the FF. Nearly identical conversion efficiency is preserved for both TCO substrates. Excellent c-axis orientation even at low growth temperature promises improved device performance by extended parametric optimization.
Hybrid Training Method for MLP: Optimization of Architecture and Training.
Zanchettin, C; Ludermir, T B; Almeida, L M
2011-08-01
The performance of an artificial neural network (ANN) depends upon the selection of proper connection weights, network architecture, and cost function during network training. This paper presents a hybrid approach (GaTSa) to optimize the performance of the ANN in terms of architecture and weights. GaTSa is an extension of a previous method (TSa) proposed by the authors. GaTSa is based on the integration of the heuristic simulated annealing (SA), tabu search (TS), genetic algorithms (GA), and backpropagation, whereas TSa does not use GA. The main advantages of GaTSa are the following: a constructive process to add new nodes in the architecture based on GA, the ability to escape from local minima with uphill moves (SA feature), and faster convergence by the evaluation of a set of solutions (TS feature). The performance of GaTSa is investigated through an empirical evaluation of 11 public-domain data sets using different cost functions in the simultaneous optimization of the multilayer perceptron ANN architecture and weights. Experiments demonstrated that GaTSa can also be used for relevant feature selection. GaTSa presented statistically relevant results in comparison with other global and local optimization techniques.
NASA Astrophysics Data System (ADS)
Zhou, Naiyun; Gao, Yi
2017-03-01
This paper presents a fully automatic approach to grade intermediate prostate malignancy with hematoxylin and eosin-stained whole slide images. Deep learning architectures such as convolutional neural networks have been utilized in the domain of histopathology for automated carcinoma detection and classification. However, few work show its power in discriminating intermediate Gleason patterns, due to sporadic distribution of prostate glands on stained surgical section samples. We propose optimized hematoxylin decomposition on localized images, followed by convolutional neural network to classify Gleason patterns 3+4 and 4+3 without handcrafted features or gland segmentation. Crucial glands morphology and structural relationship of nuclei are extracted twice in different color space by the multi-scale strategy to mimic pathologists' visual examination. Our novel classification scheme evaluated on 169 whole slide images yielded a 70.41% accuracy and corresponding area under the receiver operating characteristic curve of 0.7247.
Pan, Hongye; Zhang, Qing; Cui, Keke; Chen, Guoquan; Liu, Xuesong; Wang, Longhu
2017-05-01
The extraction of linarin from Flos chrysanthemi indici by ethanol was investigated. Two modeling techniques, response surface methodology and artificial neural network, were adopted to optimize the process parameters, such as, ethanol concentration, extraction period, extraction frequency, and solvent to material ratio. We showed that both methods provided good predictions, but artificial neural network provided a better and more accurate result. The optimum process parameters include, ethanol concentration of 74%, extraction period of 2 h, extraction three times, solvent to material ratio of 12 mL/g. The experiment yield of linarin was 90.5% that deviated less than 1.6% from that obtained by predicted result. © 2017 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.
Genetic algorithm reveals energy-efficient waveforms for neural stimulation.
Wongsarnpigoon, Amorn; Grill, Warren M
2009-01-01
Energy consumption is an important consideration for battery-powered implantable stimulators. We used a genetic algorithm (GA) that mimics biological evolution to determine the energy-optimal waveform shape for neural stimulation. The GA was coupled to NEURON using a model of extracellular stimulation of a mammalian myelinated axon. Stimulation waveforms represented the organisms of a population, and each waveform's shape was encoded into genes. The fitness of each waveform was based on its energy efficiency and ability to elicit an action potential. After each generation of the GA, waveforms mated to produce offspring waveforms, and a new population was formed consisting of the offspring and the fittest waveforms of the previous generation. Over the course of the GA, waveforms became increasingly energy-efficient and converged upon a highly energy-efficient shape. The resulting waveforms resembled truncated normal curves or sinusoids and were 3-74% more energy-efficient than several waveform shapes commonly used in neural stimulation. If implemented in implantable neural stimulators, the GA optimized waveforms could prolong battery life, thereby reducing the costs and risks of battery-replacement surgery.
Genetic Algorithm Reveals Energy-Efficient Waveforms for Neural Stimulation
Wongsarnpigoon, Amorn; Grill, Warren M.
2013-01-01
Energy consumption is an important consideration for battery-powered implantable stimulators. We used a genetic algorithm (GA) that mimics biological evolution to determine the energy-optimal waveform shape for neural stimulation. The GA was coupled to NEURON using a model of extracellular stimulation of a mammalian myelinated axon. Stimulation waveforms represented the organisms of a population, and each waveform’s shape was encoded into genes. The fitness of each waveform was based on its energy efficiency and ability to elicit an action potential. After each generation of the GA, waveforms mated to produce offspring waveforms, and a new population was formed consisting of the offspring and the fittest waveforms of the previous generation. Over the course of the GA, waveforms became increasingly energy-efficient and converged upon a highly energy-efficient shape. The resulting waveforms resembled truncated normal curves or sinusoids and were 3–74% more energy-efficient than several waveform shapes commonly used in neural stimulation. If implemented in implantable neural stimulators, the GA optimized waveforms could prolong battery life, thereby reducing the costs and risks of battery-replacement surgery. PMID:19964233
NASA Astrophysics Data System (ADS)
Cheng, Ke; Han, Kaikai; Kuang, Zhongcheng; Jin, Ranran; Hu, Junxia; Guo, Longfei; Liu, Ya; Lu, Zhangbo; Du, Zuliang
2017-04-01
In this work, CuInGa alloy precursor films are fabricated by co-sputtering of CuIn and CuGa targets simultaneously. After selenization in a tube-type rapid thermal annealing system under a Se atmosphere, the Cu(In, Ga)Se2 (CIGS) absorber layers are obtained. Standard soda lime glass (SLG)/Mo/CIGS/CdS/i-ZnO/ITO/Ag grid structural solar cells are fabricated based on the selenized CIGS absorbers. The influences of selenization temperatures on the composition, crystallinity, and device performances are systematically investigated by x-ray energy dispersive spectroscopy, x-ray diffraction, Raman spectroscopy, and the current density-voltage ( J- V) measurement. It is found that the elemental ratio of Cu/(In + Ga) strongly depends on the selenization temperatures. Because of the appropriate elemental ratio, a 9.92% conversion efficiency is reached for the CIGS absorber selenized at 560°C. After the additional optimization by pre-annealing treatment at 280°C before the selenization, a highest conversion efficiency of 11.19% with a open-circuit ( V oc) of 456 mV, a short-circuit ( J sc) of 40.357 mA/cm2 and a fill factor of 60.82% without antireflection coating has been achieved. Above 13% efficiency improvement was achievable. Our experimental findings presented in this work demonstrate that the post-selenization of co-sputtered CuIn and CuGa precursor is a promising way to fabricate high quality CIGS absorbers.
NASA Astrophysics Data System (ADS)
Wu, Dan; Tang, Xiaohong; Wang, Kai; Li, Xianqiang
2017-04-01
Semiconductor nanowires(NWs) with subwavelength scale diameters have demonstrated superior light trapping features, which unravel a new pathway for low cost and high efficiency future generation solar cells. Unlike other published work, a fully analytic design is for the first time proposed for optimal geometrical parameters of vertically-aligned GaAs NW arrays for maximal energy harvesting. Using photocurrent density as the light absorbing evaluation standard, 2 μm length NW arrays whose multiple diameters and periodicity are quantitatively identified achieving the maximal value of 29.88 mA/cm2 under solar illumination. It also turns out that our method has wide suitability for single, double and four different diameters of NW arrays for highest photon energy harvesting. To validate this analytical method, intensive numerical three-dimensional finite-difference time-domain simulations of the NWs’ light harvesting are also carried out. Compared with the simulation results, the predicted maximal photocurrent densities lie within 1.5% tolerance for all cases. Along with the high accuracy, through directly disclosing the exact geometrical dimensions of NW arrays, this method provides an effective and efficient route for high performance photovoltaic design.
Optimized laser patterning for high performance Cu(In,Ga)Se2 thin-film solar modules
NASA Astrophysics Data System (ADS)
Burn, Andreas; Muralt, Martin; Witte, Reiner; Buecheler, Stephan; Nishiwaki, Shiro; Krainer, Lukas; Spuehler, Gabriel J.; Romano, Valerio
2014-03-01
The thin-film solar cell market has seen a period of consolidation during the last years and many involved companies were forced to stop production due to increasing price pressure from competing cell technologies. Today, thin-film solar industry is gaining momentum again. Especially Cu(In,Ga)Se2 technology evolves at high pace fired by recently achieved record efficiencies of 20.4 percent on flexible polyimide substrate [1] and 20.8 percent on glass substrate [2]. Fresh companies are preparing market entry with matured products and manufacturing technology suitable for high-volume and high-throughput production. Among these key-enabling technologies is laser patterning for cell-to-cell interconnects. Several research groups worked on efficient and reliable laser processes that are now ready for the industrial assessment. Here we present a set of work-horse processes for P1, P2 and P3 scribing of CIGS cells on glass substrate. Optimized parameters are presented for 532 nm and 1064 nm using 50 ps pulses from an all-in-fiber laser system. We further demonstrate the successful realization of functional 8-cell modules with a reduced "dead-zone" width of 70±5 μm and high efficiencies. The certified efficiency of 16.6 percent for our low-dead-zone champion module confirms the observation that shrinking of interconnects has no adverse effects on their electrical quality.
Biefeld, R.M.; Baucom, K.C.; Follstaedt, D.M.; Kurtz, S.R.
1994-08-01
We have prepared InAsSb/InGaAs strained-layer superlattices (SLSs) by metal-organic chemical vapor deposition using a variety of growth conditions. Presence of an InGaAsSb interface layer was indicated by x-ray diffraction. This interface effect was minimized by optimizing the purge times, reactant flows, and growth conditions. The optimized growth conditions involved the use of low pressure, short purge times between the growth of the layers, and no reactant flow during the purges. Electron diffraction indicates that CuPt-type compositional ordering occurs in InAs{sub 1{minus}x}Sb{sub x} alloys and SLSs which explains an observed bandgap reduction from previously accepted alloy values.
The Neural Code for Auditory Space Depends on Sound Frequency and Head Size in an Optimal Manner
Harper, Nicol S.; Scott, Brian H.; Semple, Malcolm N.; McAlpine, David
2014-01-01
A major cue to the location of a sound source is the interaural time difference (ITD)–the difference in sound arrival time at the two ears. The neural representation of this auditory cue is unresolved. The classic model of ITD coding, dominant for a half-century, posits that the distribution of best ITDs (the ITD evoking a neuron’s maximal response) is unimodal and largely within the range of ITDs permitted by head-size. This is often interpreted as a place code for source location. An alternative model, based on neurophysiology in small mammals, posits a bimodal distribution of best ITDs with exquisite sensitivity to ITDs generated by means of relative firing rates between the distributions. Recently, an optimal-coding model was proposed, unifying the disparate features of these two models under the framework of efficient coding by neural populations. The optimal-coding model predicts that distributions of best ITDs depend on head size and sound frequency: for high frequencies and large heads it resembles the classic model, for low frequencies and small head sizes it resembles the bimodal model. The optimal-coding model makes key, yet unobserved, predictions: for many species, including humans, both forms of neural representation are employed, depending on sound frequency. Furthermore, novel representations are predicted for intermediate frequencies. Here, we examine these predictions in neurophysiological data from five mammalian species: macaque, guinea pig, cat, gerbil and kangaroo rat. We present the first evidence supporting these untested predictions, and demonstrate that different representations appear to be employed at different sound frequencies in the same species. PMID:25372405
The neural code for auditory space depends on sound frequency and head size in an optimal manner.
Harper, Nicol S; Scott, Brian H; Semple, Malcolm N; McAlpine, David
2014-01-01
A major cue to the location of a sound source is the interaural time difference (ITD)-the difference in sound arrival time at the two ears. The neural representation of this auditory cue is unresolved. The classic model of ITD coding, dominant for a half-century, posits that the distribution of best ITDs (the ITD evoking a neuron's maximal response) is unimodal and largely within the range of ITDs permitted by head-size. This is often interpreted as a place code for source location. An alternative model, based on neurophysiology in small mammals, posits a bimodal distribution of best ITDs with exquisite sensitivity to ITDs generated by means of relative firing rates between the distributions. Recently, an optimal-coding model was proposed, unifying the disparate features of these two models under the framework of efficient coding by neural populations. The optimal-coding model predicts that distributions of best ITDs depend on head size and sound frequency: for high frequencies and large heads it resembles the classic model, for low frequencies and small head sizes it resembles the bimodal model. The optimal-coding model makes key, yet unobserved, predictions: for many species, including humans, both forms of neural representation are employed, depending on sound frequency. Furthermore, novel representations are predicted for intermediate frequencies. Here, we examine these predictions in neurophysiological data from five mammalian species: macaque, guinea pig, cat, gerbil and kangaroo rat. We present the first evidence supporting these untested predictions, and demonstrate that different representations appear to be employed at different sound frequencies in the same species.
Sikora, R.; Chady, T.; Baniukiewicz, P.; Caryk, M.; Piekarczyk, B.
2010-02-22
Nondestructive testing and evaluation are under continuous development. Currently researches are concentrated on three main topics: advancement of existing methods, introduction of novel methods and development of artificial intelligent systems for automatic defect recognition (ADR). Automatic defect classification algorithm comprises of two main tasks: creating a defect database and preparing a defect classifier. Here, the database was built using defect features that describe all geometrical and texture properties of the defect. Almost twenty carefully selected features calculated for flaws extracted from real radiograms were used. The radiograms were obtained from shipbuilding industry and they were verified by qualified operator. Two weld defect's classifiers based on artificial neural networks were proposed and compared. First model consisted of one neural network model, where each output neuron corresponded to different defect group. The second model contained five neural networks. Each neural network had one neuron on output and was responsible for detection of defects from one group. In order to evaluate the effectiveness of the neural networks classifiers, the mean square errors were calculated for test radiograms and compared.
Mehrotra, Shakti; Prakash, O; Khan, Feroz; Kukreja, A K
2013-02-01
KEY MESSAGE : ANN-based combinatorial model is proposed and its efficiency is assessed for the prediction of optimal culture conditions to achieve maximum productivity in a bioprocess in terms of high biomass. A neural network approach is utilized in combination with Hidden Markov concept to assess the optimal values of different environmental factors that result in maximum biomass productivity of cultured tissues after definite culture duration. Five hidden Markov models (HMMs) were derived for five test culture conditions, i.e. pH of liquid growth medium, volume of medium per culture vessel, sucrose concentration (%w/v) in growth medium, nitrate concentration (g/l) in the medium and finally the density of initial inoculum (g fresh weight) per culture vessel and their corresponding fresh weight biomass. The artificial neural network (ANN) model was represented as the function of these five Markov models, and the overall simulation of fresh weight biomass was done with this combinatorial ANN-HMM. The empirical results of Rauwolfia serpentina hairy roots were taken as model and compared with simulated results obtained from pure ANN and ANN-HMMs. The stochastic testing and Cronbach's α-value of pure and combinatorial model revealed more internal consistency and skewed character (0.4635) in histogram of ANN-HMM compared to pure ANN (0.3804). The simulated results for optimal conditions of maximum fresh weight production obtained from ANN-HMM and ANN model closely resemble the experimentally optimized culture conditions based on which highest fresh weight was obtained. However, only 2.99 % deviation from the experimental values could be observed in the values obtained from combinatorial model when compared to the pure ANN model (5.44 %). This comparison showed 45 % better potential of combinatorial model for the prediction of optimal culture conditions for the best growth of hairy root cultures.
Cassidy, Andrew S; Georgiou, Julius; Andreou, Andreas G
2013-09-01
We present a design framework for neuromorphic architectures in the nano-CMOS era. Our approach to the design of spiking neurons and STDP learning circuits relies on parallel computational structures where neurons are abstracted as digital arithmetic logic units and communication processors. Using this approach, we have developed arrays of silicon neurons that scale to millions of neurons in a single state-of-the-art Field Programmable Gate Array (FPGA). We demonstrate the validity of the design methodology through the implementation of cortical development in a circuit of spiking neurons, STDP synapses, and neural architecture optimization. Copyright © 2013 Elsevier Ltd. All rights reserved.
2011-12-01
in advanced RF systems. Towards this end, we have performed drift-diffusion-based simulations of a GaN HEMT operating as a class A amplifier . 2...reducing the burden, to Department of Defense, Washington Headquarters Services, Directorate for Information Operations and Reports (0704-0188...optimize device performance by determining which part of the device to modify for greatest impact. 15. SUBJECT TERMS Power amplifier , distortion 16
Pruning Neural Networks with Distribution Estimation Algorithms
Cantu-Paz, E
2003-01-15
This paper describes the application of four evolutionary algorithms to the pruning of neural networks used in classification problems. Besides of a simple genetic algorithm (GA), the paper considers three distribution estimation algorithms (DEAs): a compact GA, an extended compact GA, and the Bayesian Optimization Algorithm. The objective is to determine if the DEAs present advantages over the simple GA in terms of accuracy or speed in this problem. The experiments used a feed forward neural network trained with standard back propagation and public-domain and artificial data sets. The pruned networks seemed to have better or equal accuracy than the original fully-connected networks. Only in a few cases, pruning resulted in less accurate networks. We found few differences in the accuracy of the networks pruned by the four EAs, but found important differences in the execution time. The results suggest that a simple GA with a small population might be the best algorithm for pruning networks on the data sets we tested.
Saeidi, Iman; Barfi, Behruz; Asghari, Alireza; Gharahbagh, Abdorreza Alavi; Barfi, Azadeh; Peyrovi, Moazameh; Afsharzadeh, Maryam; Hojatinasab, Mostafa
2015-10-01
A novel and environmentally friendly ionic-liquid-based hollow-fiber liquid-phase microextraction method combined with a hybrid artificial neural network (ANN)-genetic algorithm (GA) strategy was developed for ferro and ferric ions speciation as model analytes. Different parameters such as type and volume of extraction solvent, amounts of chelating agent, volume and pH of sample, ionic strength, stirring rate, and extraction time were investigated. Much more effective parameters were firstly examined based on one-variable-at-a-time design, and obtained results were used to construct an independent model for each parameter. The models were then applied to achieve the best and minimum numbers of candidate points as inputs for the ANN process. The maximum extraction efficiencies were achieved after 9 min using 22.0 μL of 1-hexyl-3-methylimidazolium hexafluorophosphate ([C6MIM][PF6]) as the acceptor phase and 10 mL of sample at pH = 7.0 containing 64.0 μg L(-1) of benzohydroxamic acid (BHA) as the complexing agent, after the GA process. Once optimized, analytical performance of the method was studied in terms of linearity (1.3-316 μg L(-1), R (2) = 0.999), accuracy (recovery = 90.1-92.3%), and precision (relative standard deviation (RSD) <3.1). Finally, the method was successfully applied to speciate the iron species in the environmental and wastewater samples.
Pennings, Jeroen L A; Theunissen, Peter T; Piersma, Aldert H
2012-10-28
The murine neural embryonic stem cell test (ESTn) is an in vitro model for neurodevelopmental toxicity testing. Recent studies have shown that application of transcriptomics analyses in the ESTn is useful for obtaining more accurate predictions as well as mechanistic insights. Gene expression responses due to stem cell neural differentiation versus toxicant exposure could be distinguished using the Principal Component Analysis based differentiation track algorithm. In this study, we performed a de novo analysis on combined raw data (10 compounds, 19 exposures) from three previous transcriptomics studies to identify an optimized gene set for neurodevelopmental toxicity prediction in the ESTn. By evaluating predictions of 200,000 randomly selected gene sets, we identified genes which significantly contributed to the prediction reliability. A set of 100 genes was obtained, predominantly involved in (neural) development. Further stringency restrictions resulted in a set of 29 genes that allowed for 84% prediction accuracy (area under the curve 94%). We anticipate these gene sets will contribute to further improve ESTn transcriptomics studies aimed at compound risk assessment.
Luo, Biao; Wu, Huai-Ning
2012-12-01
This paper addresses the approximate optimal control problem for a class of parabolic partial differential equation (PDE) systems with nonlinear spatial differential operators. An approximate optimal control design method is proposed on the basis of the empirical eigenfunctions (EEFs) and neural network (NN). First, based on the data collected from the PDE system, the Karhunen-Loève decomposition is used to compute the EEFs. With those EEFs, the PDE system is formulated as a high-order ordinary differential equation (ODE) system. To further reduce its dimension, the singular perturbation (SP) technique is employed to derive a reduced-order model (ROM), which can accurately describe the dominant dynamics of the PDE system. Second, the Hamilton-Jacobi-Bellman (HJB) method is applied to synthesize an optimal controller based on the ROM, where the closed-loop asymptotic stability of the high-order ODE system can be guaranteed by the SP theory. By dividing the optimal control law into two parts, the linear part is obtained by solving an algebraic Riccati equation, and a new type of HJB-like equation is derived for designing the nonlinear part. Third, a control update strategy based on successive approximation is proposed to solve the HJB-like equation, and its convergence is proved. Furthermore, an NN approach is used to approximate the cost function. Finally, we apply the developed approximate optimal control method to a diffusion-reaction process with a nonlinear spatial operator, and the simulation results illustrate its effectiveness.
Subramanian, Narayanaswamy; Yajnik, Archit; Murthy, Rayasa S Ramachandra
2004-02-02
The objective of the study was to optimize the formulation parameters of cytarabine liposomes by using artificial neural networks (ANN) and multiple regression analysis using 3(3) factorial design (FD). As model formulations, 27 formulations were prepared. The formulation variables, drug (cytarabine)/lipid (phosphatidyl choline [PC] and cholesterol [Chol]) molar ratio (X1), PC/Chol in percentage ratio of total lipids (X2), and the volume of hydration medium (X3) were selected as the independent variables; and the percentage drug entrapment (PDE) was selected as the dependent variable. A set of causal factors was used as tutorial data for ANN and fed into a computer. The optimization was performed by minimizing the generalized distance between the predicted values of each response and the optimized one that was obtained individually. In case of 3(3) factorial design, a second-order full-model polynomial equation and a reduced model were established by subjecting the transformed values of independent variables to multiple regression analysis, and contour plots were drawn using the equation. The optimization methods developed by both ANN and FD were validated by preparing another 5 liposomal formulations. The predetermined PDE and the experimental data were compared with predicted data by paired t test, no statistically significant difference was observed. ANN showed less error compared with multiple regression analysis. These findings demonstrate that ANN provides more accurate prediction and is quite useful in the optimization of pharmaceutical formulations when compared with the multiple regression analysis method.
Li, Zhongwei; Sun, Beibei; Xin, Yuezhen; Wang, Xun
2016-01-01
Flavones, the secondary metabolites of Phellinus igniarius fungus, have the properties of antioxidation and anticancer. Because of the great medicinal value, there are large demands on flavones for medical use and research. Flavones abstracted from natural Phellinus can not meet the medical and research need, since Phellinus in the natural environment is very rare and is hard to be cultivated artificially. The production of flavones is mainly related to the fermentation culture of Phellinus, which made the optimization of culture conditions an important problem. Some researches were made to optimize the fermentation culture conditions, such as the method of response surface methodology, which claimed the optimal flavones production was 1532.83 μg/mL. In order to further optimize the fermentation culture conditions for flavones, in this work a hybrid intelligent algorithm with genetic algorithm and BP neural network is proposed. Our method has the intelligent learning ability and can overcome the limitation of large-scale biotic experiments. Through simulations, the optimal culture conditions are obtained and the flavones production is increased to 2200 μg/mL. PMID:27595102
Li, Zhongwei; Sun, Beibei; Xin, Yuezhen; Wang, Xun; Zhu, Hu
2016-01-01
Flavones, the secondary metabolites of Phellinus igniarius fungus, have the properties of antioxidation and anticancer. Because of the great medicinal value, there are large demands on flavones for medical use and research. Flavones abstracted from natural Phellinus can not meet the medical and research need, since Phellinus in the natural environment is very rare and is hard to be cultivated artificially. The production of flavones is mainly related to the fermentation culture of Phellinus, which made the optimization of culture conditions an important problem. Some researches were made to optimize the fermentation culture conditions, such as the method of response surface methodology, which claimed the optimal flavones production was 1532.83 μg/mL. In order to further optimize the fermentation culture conditions for flavones, in this work a hybrid intelligent algorithm with genetic algorithm and BP neural network is proposed. Our method has the intelligent learning ability and can overcome the limitation of large-scale biotic experiments. Through simulations, the optimal culture conditions are obtained and the flavones production is increased to 2200 μg/mL.
Han, Zong-wei; Huang, Wei; Luo, Yun; Zhang, Chun-di; Qi, Da-cheng
2015-03-01
Taking the soil organic matter in eastern Zhongxiang County, Hubei Province, as a research object, thirteen sample sets from different regions were arranged surrounding the road network, the spatial configuration of which was optimized by the simulated annealing approach. The topographic factors of these thirteen sample sets, including slope, plane curvature, profile curvature, topographic wetness index, stream power index and sediment transport index, were extracted by the terrain analysis. Based on the results of optimization, a multiple linear regression model with topographic factors as independent variables was built. At the same time, a multilayer perception model on the basis of neural network approach was implemented. The comparison between these two models was carried out then. The results revealed that the proposed approach was practicable in optimizing soil sampling scheme. The optimal configuration was capable of gaining soil-landscape knowledge exactly, and the accuracy of optimal configuration was better than that of original samples. This study designed a sampling configuration to study the soil attribute distribution by referring to the spatial layout of road network, historical samples, and digital elevation data, which provided an effective means as well as a theoretical basis for determining the sampling configuration and displaying spatial distribution of soil organic matter with low cost and high efficiency.
NASA Astrophysics Data System (ADS)
Chen, Ying; Liu, Teng; Wang, Wenyue; Zhu, Qiguang; Bi, Weihong
2015-04-01
According to the band gap and photon localization characteristics, the single-arm notching and the double-arm notching Mach-Zehnder interferometer (MZI) structures based on 2D triangular lattice air hole-typed photonic crystal waveguide are proposed. The back-propagation (BP) neural network is introduced to optimize the structural parameters of the photonic crystal MZI structure, which results in the normalized transmission peak increasing from 85.3% to 97.1%. The sensitivity performances of the two structures are compared and analyzed using the Salmonella solution samples with different concentrations in the numerical simulation. The results show that the sensitivity of the double-arm notching structure is 4583 nm/RIU, which is about 6.4 times of the single-arm notching structure, which can provide some references for the optimization of the photonic devices and the design of high-sensitivity biosensors.
Hall, L Mark; Hill, Dennis W; Menikarachchi, Lochana C; Chen, Ming-Hui; Hall, Lowell H; Grant, David F
2015-01-01
Artificial Neural Networks (ANN) are extensively used to model 'omics' data. Different modeling methodologies and combinations of adjustable parameters influence model performance and complicate model optimization. We evaluated optimization of four ANN modeling parameters (learning rate annealing, stopping criteria, data split method, network architecture) using retention index (RI) data for 390 compounds. Models were assessed by independent validation (I-Val) using newly measured RI values for 1492 compounds. The best model demonstrated an I-Val standard error of 55 RI units and was built using a Ward's clustering data split and a minimally nonlinear network architecture. Use of validation statistics for stopping and final model selection resulted in better independent validation performance than the use of test set statistics.
Buyukada, Musa
2016-09-01
Co-combustion of coal and peanut hull (PH) were investigated using artificial neural networks (ANN), particle swarm optimization, and Monte Carlo simulation as a function of blend ratio, heating rate, and temperature. The best prediction was reached by ANN61 multi-layer perception model with a R(2) of 0.99994. Blend ratio of 90 to 10 (PH to coal, wt%), temperature of 305°C, and heating rate of 49°Cmin(-1) were determined as the optimum input values and yield of 87.4% was obtained under PSO optimized conditions. The validation experiments resulted in yields of 87.5%±0.2 after three replications. Monte Carlo simulations were used for the probabilistic assessments of stochastic variability and uncertainty associated with explanatory variables of co-combustion process.
Optimizing growth and post treatment of diamond for high capacitance neural interfaces.
Tong, Wei; Fox, Kate; Zamani, Akram; Turnley, Ann M; Ganesan, Kumaravelu; Ahnood, Arman; Cicione, Rosemary; Meffin, Hamish; Prawer, Steven; Stacey, Alastair; Garrett, David J
2016-10-01
Electrochemical and biological properties are two crucial criteria in the selection of the materials to be used as electrodes for neural interfaces. For neural stimulation, materials are required to exhibit high capacitance and to form intimate contact with neurons for eliciting effective neural responses at acceptably low voltages. Here we report on a new high capacitance material fabricated using nitrogen included ultrananocrystalline diamond (N-UNCD). After exposure to oxygen plasma for 3 h, the activated N-UNCD exhibited extremely high electrochemical capacitance greater than 1 mF/cm(2), which originates from the special hybrid sp(2)/sp(3) structure of N-UNCD. The in vitro biocompatibility of the activated N-UNCD was then assessed using rat cortical neurons and surface roughness was found to be critical for healthy neuron growth, with best results observed on surfaces with a roughness of approximately 20 nm. Therefore, by using oxygen plasma activated N-UNCD with appropriate surface roughness, and considering the chemical and mechanical stability of diamond, the fabricated neural interfaces are expected to exhibit high efficacy, long-term stability and a healthy neuron/electrode interface.
NASA Astrophysics Data System (ADS)
Paegert, Martin; Stassun, Keivan G.; Burger, Dan M.
2014-08-01
We describe a new neural-net-based light curve classifier and provide it with documentation as a ready-to-use tool for the community. While optimized for identification and classification of eclipsing binary stars, the classifier is general purpose, and has been developed for speed in the context of upcoming massive surveys such as the Large Synoptic Survey Telescope. A challenge for classifiers in the context of neural-net training and massive data sets is to minimize the number of parameters required to describe each light curve. We show that a simple and fast geometric representation that encodes the overall light curve shape, together with a chi-square parameter to capture higher-order morphology information results in efficient yet robust light curve classification, especially for eclipsing binaries. Testing the classifier on the ASAS light curve database, we achieve a retrieval rate of 98% and a false-positive rate of 2% for eclipsing binaries. We achieve similarly high retrieval rates for most other periodic variable-star classes, including RR Lyrae, Mira, and delta Scuti. However, the classifier currently has difficulty discriminating between different sub-classes of eclipsing binaries, and suffers a relatively low (~60%) retrieval rate for multi-mode delta Cepheid stars. We find that it is imperative to train the classifier's neural network with exemplars that include the full range of light curve quality to which the classifier will be expected to perform; the classifier performs well on noisy light curves only when trained with noisy exemplars. The classifier source code, ancillary programs, a trained neural net, and a guide for use, are provided.
Paegert, Martin; Stassun, Keivan G.; Burger, Dan M.
2014-08-01
We describe a new neural-net-based light curve classifier and provide it with documentation as a ready-to-use tool for the community. While optimized for identification and classification of eclipsing binary stars, the classifier is general purpose, and has been developed for speed in the context of upcoming massive surveys such as the Large Synoptic Survey Telescope. A challenge for classifiers in the context of neural-net training and massive data sets is to minimize the number of parameters required to describe each light curve. We show that a simple and fast geometric representation that encodes the overall light curve shape, together with a chi-square parameter to capture higher-order morphology information results in efficient yet robust light curve classification, especially for eclipsing binaries. Testing the classifier on the ASAS light curve database, we achieve a retrieval rate of 98% and a false-positive rate of 2% for eclipsing binaries. We achieve similarly high retrieval rates for most other periodic variable-star classes, including RR Lyrae, Mira, and delta Scuti. However, the classifier currently has difficulty discriminating between different sub-classes of eclipsing binaries, and suffers a relatively low (∼60%) retrieval rate for multi-mode delta Cepheid stars. We find that it is imperative to train the classifier's neural network with exemplars that include the full range of light curve quality to which the classifier will be expected to perform; the classifier performs well on noisy light curves only when trained with noisy exemplars. The classifier source code, ancillary programs, a trained neural net, and a guide for use, are provided.
Zhou, Fuqiang; Su, Zhen; Chai, Xinghua; Chen, Lipeng
2014-01-01
This paper proposes a new method to detect and identify foreign matter mixed in a plastic bottle filled with transfusion solution. A spin-stop mechanism and mixed illumination style are applied to obtain high contrast images between moving foreign matter and a static transfusion background. The Gaussian mixture model is used to model the complex background of the transfusion image and to extract moving objects. A set of features of moving objects are extracted and selected by the ReliefF algorithm, and optimal feature vectors are fed into the back propagation (BP) neural network to distinguish between foreign matter and bubbles. The mind evolutionary algorithm (MEA) is applied to optimize the connection weights and thresholds of the BP neural network to obtain a higher classification accuracy and faster convergence rate. Experimental results show that the proposed method can effectively detect visible foreign matter in 250-mL transfusion bottles. The misdetection rate and false alarm rate are low, and the detection accuracy and detection speed are satisfactory. PMID:25347581
Rozak, David A; Orban, John; Bryan, Philip N
2005-12-01
The third albumin binding domain of streptococcal protein G strain 148 (G148-GA3) belongs to a novel class of prokaryotic albumin binding modules that is thought to support virulence in several bacterial species. Here, we characterize G148-GA3 folding and albumin binding by using differential scanning calorimetry and isothermal titration calorimetry to obtain the most complete set of thermodynamic state functions for any member of this medically significant module. When buffered at pH 7.0 the 46-amino acid alpha-helical domain melts at 72 degrees C and exhibits marginal stability (15 kJ/mol) at 37 degrees C. G148-GA3 unfolding is characterized by small contributions to entropy from non-hydrophobic forces and a low DeltaCp (1.1 kJ/(deg mol)). Isothermal titration calorimetry reveals that the domain has evolved to optimally bind human serum albumin near 37 degrees C with a binding constant of 1.4 x 10 7 M(-1). Analysis of G148-GA3 thermodynamics suggests that the domain experiences atypically small per residue changes in structural dynamics and heat capacity while transiting between folded and unfolded states.
Ansah-Antwi, KwaDwo Konadu Chua, Soo Jin; Soh, Chew Beng; Liu, Hongfei
2015-11-15
The four nearest Si(111) multifaceted sidewalls were exposed inside an array of 3 μm-wide square holes patterned on an Si(100) substrate, and this patterned Si(100) substrate was used as a substrate for the deposition of a gallium nitride (GaN) epilayer. Subsequently the effect that the growth pressure, the etched-hole profiles, and the etched-hole arrangement had upon the quality of the as-grown GaN was investigated. The coalescence of the as-grown GaN epilayer on the exposed Si(111) facets was observed to be enhanced with reduced growth pressure from 120 to 90 Torr. A larger Si(001) plane area at the bottom of the etched holes resulted in bidirectional GaN domains, which resulted in poor material quality. The bidirectional GaN domains were observed as two sets of six peaks via a high-resolution x-ray diffraction phi scan of the GaN(10-11) reflection. It was also shown that a triangular array of etched holes was more desirable than square arrays of etched holes for the growth high-quality and continuous GaN films.
Karacay, Habibe; Sharkey, Robert M; McBride, William J; Rossi, Edmund A; Chang, Chien-Hsing; Goldenberg, David M
2011-04-01
Bispecific antibody pretargeting is highly sensitive and specific for cancer detection by PET. In this study, the preparation of a high-specific-activity (68)Ga-labeled hapten-peptide, IMP288, was evaluated. IMP288 (DOTA-D-Tyr-D-Lys(histamine-succinyl-glycine [HSG])-D-glu-D-Lys(HSG)-NH(2)) was added to buffered (68)Ga and then heated in boiling water and purified on a reversed-phase cartridge. Tumor-bearing nude mice were used for biodistribution and tumor localization studies. (68)Ga-IMP288 was prepared at a starting specific activity up to 1.78 GBq/nmol, with final yields of 0.74 GBq/nmol (decay-corrected) and less than 1% unbound (68)Ga. Purification was essential to remove unbound (68)Ga and (68)Ge breakthrough. Pretargeted animals showed a high (68)Ga-IMP288 uptake (27.5 ± 5.8 percentage injected dose per gram), with ratios of 13.6 ± 4.8, 66.8 ± 14.5, and 325.9 ± 61.9 for the kidneys, liver, and blood, respectively, at 1.5 h after peptide injection. High-specific-activity labeling of DOTA-hapten-peptide was obtained from the (68)Ga/(68)Ge generator for approximately 1 y, yielding products suitable for immunoPET.
NASA Astrophysics Data System (ADS)
Ai, Yuewei; Shao, Xinyu; Jiang, Ping; Li, Peigen; Liu, Yang; Yue, Chen
2015-11-01
The welded joints of dissimilar materials have been widely used in automotive, ship and space industries. The joint quality is often evaluated by weld seam geometry, microstructures and mechanical properties. To obtain the desired weld seam geometry and improve the quality of welded joints, this paper proposes a process modeling and parameter optimization method to obtain the weld seam with minimum width and desired depth of penetration for laser butt welding of dissimilar materials. During the process, Taguchi experiments are conducted on the laser welding of the low carbon steel (Q235) and stainless steel (SUS301L-HT). The experimental results are used to develop the radial basis function neural network model, and the process parameters are optimized by genetic algorithm. The proposed method is validated by a confirmation experiment. Simultaneously, the microstructures and mechanical properties of the weld seam generated from optimal process parameters are further studied by optical microscopy and tensile strength test. Compared with the unoptimized weld seam, the welding defects are eliminated in the optimized weld seam and the mechanical properties are improved. The results show that the proposed method is effective and reliable for improving the quality of welded joints in practical production.
Silva, Leonardo W. T.; Barros, Vitor F.; Silva, Sandro G.
2014-01-01
In launching operations, Rocket Tracking Systems (RTS) process the trajectory data obtained by radar sensors. In order to improve functionality and maintenance, radars can be upgraded by replacing antennas with parabolic reflectors (PRs) with phased arrays (PAs). These arrays enable the electronic control of the radiation pattern by adjusting the signal supplied to each radiating element. However, in projects of phased array radars (PARs), the modeling of the problem is subject to various combinations of excitation signals producing a complex optimization problem. In this case, it is possible to calculate the problem solutions with optimization methods such as genetic algorithms (GAs). For this, the Genetic Algorithm with Maximum-Minimum Crossover (GA-MMC) method was developed to control the radiation pattern of PAs. The GA-MMC uses a reconfigurable algorithm with multiple objectives, differentiated coding and a new crossover genetic operator. This operator has a different approach from the conventional one, because it performs the crossover of the fittest individuals with the least fit individuals in order to enhance the genetic diversity. Thus, GA-MMC was successful in more than 90% of the tests for each application, increased the fitness of the final population by more than 20% and reduced the premature convergence. PMID:25196013
Wang, Zhiliang; Zong, Xu; Gao, Yuying; Han, Jingfeng; Xu, Zhiqiang; Li, Zheng; Ding, Chunmei; Wang, Shengyang; Li, Can
2017-09-13
Photoelectrochemical water splitting provides an attractive way to store solar energy in molecular hydrogen as a kind of sustainable fuel. To achieve high solar conversion efficiency, the most stringent criteria are effective charge separation and injection in electrodes. Herein, efficient photoelectrochemical water oxidation is realized by optimizing charge separation and surface charge transfer of GaN:ZnO photoanode. The charge separation can be greatly improved through modified moisture-assisted nitridation and HCl acid treatment, by which the interfaces in GaN:ZnO solid solution particles are optimized and recombination centers existing at the interfaces are depressed in GaN:ZnO photoanode. Moreover, a multimetal phosphide of NiCoFeP was employed as water oxidation cocatalyst to improve the charge injection at the photoanode/electrolyte interface. Consequently, it significantly decreases the overpotential and brings the photocurrent to a benchmark of 3.9 mA cm(-2) at 1.23 V vs RHE and a solar conversion efficiency over 1% was obtained.
Silva, Leonardo W T; Barros, Vitor F; Silva, Sandro G
2014-08-18
In launching operations, Rocket Tracking Systems (RTS) process the trajectory data obtained by radar sensors. In order to improve functionality and maintenance, radars can be upgraded by replacing antennas with parabolic reflectors (PRs) with phased arrays (PAs). These arrays enable the electronic control of the radiation pattern by adjusting the signal supplied to each radiating element. However, in projects of phased array radars (PARs), the modeling of the problem is subject to various combinations of excitation signals producing a complex optimization problem. In this case, it is possible to calculate the problem solutions with optimization methods such as genetic algorithms (GAs). For this, the Genetic Algorithm with Maximum-Minimum Crossover (GA-MMC) method was developed to control the radiation pattern of PAs. The GA-MMC uses a reconfigurable algorithm with multiple objectives, differentiated coding and a new crossover genetic operator. This operator has a different approach from the conventional one, because it performs the crossover of the fittest individuals with the least fit individuals in order to enhance the genetic diversity. Thus, GA-MMC was successful in more than 90% of the tests for each application, increased the fitness of the final population by more than 20% and reduced the premature convergence.
NASA Technical Reports Server (NTRS)
Clancy, Daniel J.; Oezguener, Uemit; Graham, Ronald E.
1994-01-01
The potential for excessive plume impingement loads on Space Station Freedom solar arrays, caused by jet firings from an approaching Space Shuttle, is addressed. An artificial neural network is designed to determine commanded solar array beta gimbal angle for minimum plume loads. The commanded angle would be determined dynamically. The network design proposed involves radial basis functions as activation functions. Design, development, and simulation of this network design are discussed.
Orozco-Monteagudo, Maykel; Taboada-Crispi, Alberto; Gutierrez-Hernandez, Liliana
2008-11-06
This paper deals with the controversial topic of the selection of the parameters of a genetic algorithm, in this case hierarchical, used for training of multilayer perceptron neural networks for the binary classification. The parameters to select are the crossover and mutation probabilities of the control and parametric genes and the permanency percent. The results can be considered as a guide for using this kind of algorithm.
The Definition of Necessary Hidden Units in Neural Networks for Combinatorial Optimization
1990-01-01
Hopfield-type thermodynamic networks comprised of functionally homogenous visible units have been ap- plied to a variety of structurally simple NP-hard...has been modest and has teen generally restricted to structurallv simnle oroblems. The and most well-known aplication was cresented by:.. Tak Hozo: wo...Hofield and Tank then showed that a thermodynamic neural network with symmetri: connections and a non-linear sigmoid transfer function could effectively
NASA Astrophysics Data System (ADS)
Sellar, Richard S.
The design of multidisciplinary systems typically involves performing analyses of the system which are iterative in nature. Because the analysis of a system is composed of many parts, each potentially expensive and time-consuming, analyzing the entire system is a significant task which can only be accomplished a limited number of times during the design process. The motivation for this research is the development of a method by which the number of system analyses performed in the identification of an improved system design is reduced compared to current methods. A framework, Concurrent Discipline Design (CDD), which addresses issues associated with obtaining improved system designs in a multidisciplinary environment is presented. Concurrency in the discipline design process is achieved by constructing approximations to discipline analyses. These approximations are used to replace iteration in the analysis of the system. The framework developed in this work allows designers in various disciplines to solve approximate system design problems concurrently, using the techniques and tools with which they are experts. Solution of multidisciplinary design problems in this research is facilitated through the use of artificial neural network response surface approximations. A discussion of the capability and applicability of these approximations is presented with particular consideration given to issues regarding the potential form of the neural network approximation, scaling of neural network training data, and methods by which local gradient information can be included into neural network function approximations. Implementation of a solution strategy for multidisciplinary design problems requires the formulation of an analysis problem as a design problem. A method for casting a generic system analysis/design problem in a form which is amenable to the CDD algorithm is presented. This decomposition of the design problem into a CDD format is intended to be a flexible process
Zhang, Hao; Liu, Jia; Zhang, Qinglin
2014-01-01
Inventive conceptions amount to creative ideas for designing devices that are both original and useful. The generation of inventive conceptions is a key element of the inventive process. However, neural mechanisms of the inventive process remain poorly understood. Here we employed functional feature association tasks and event-related functional magnetic resonance imaging (MRI) to investigate neural substrates for the generation of inventive conceptions. The functional MRI (fMRI) data revealed significant activations at Brodmann area (BA) 47 in the left inferior frontal gyrus and at BA 18 in the left lingual gyrus, when participants performed biological functional feature association tasks compared with non-biological functional feature association tasks. Our results suggest that the left inferior frontal gyrus (BA 47) is associated with novelty-based representations formed by the generation and selection of semantic relatedness, and the left lingual gyrus (BA 18) is involved in relevant visual imagery in processing of semantic relatedness. The findings might shed light on neural mechanisms underlying the inventive process.
Optimizing the De-Noise Neural Network Model for GPS Time-Series Monitoring of Structures.
Kaloop, Mosbeh R; Hu, Jong Wan
2015-09-22
The Global Positioning System (GPS) is recently used widely in structures and other applications. Notwithstanding, the GPS accuracy still suffers from the errors afflicting the measurements, particularly the short-period displacement of structural components. Previously, the multi filter method is utilized to remove the displacement errors. This paper aims at using a novel application for the neural network prediction models to improve the GPS monitoring time series data. Four prediction models for the learning algorithms are applied and used with neural network solutions: back-propagation, Cascade-forward back-propagation, adaptive filter and extended Kalman filter, to estimate which model can be recommended. The noise simulation and bridge's short-period GPS of the monitoring displacement component of one Hz sampling frequency are used to validate the four models and the previous method. The results show that the Adaptive neural networks filter is suggested for de-noising the observations, specifically for the GPS displacement components of structures. Also, this model is expected to have significant influence on the design of structures in the low frequency responses and measurements' contents.
Optimizing the De-Noise Neural Network Model for GPS Time-Series Monitoring of Structures
Kaloop, Mosbeh R.; Hu, Jong Wan
2015-01-01
The Global Positioning System (GPS) is recently used widely in structures and other applications. Notwithstanding, the GPS accuracy still suffers from the errors afflicting the measurements, particularly the short-period displacement of structural components. Previously, the multi filter method is utilized to remove the displacement errors. This paper aims at using a novel application for the neural network prediction models to improve the GPS monitoring time series data. Four prediction models for the learning algorithms are applied and used with neural network solutions: back-propagation, Cascade-forward back-propagation, adaptive filter and extended Kalman filter, to estimate which model can be recommended. The noise simulation and bridge’s short-period GPS of the monitoring displacement component of one Hz sampling frequency are used to validate the four models and the previous method. The results show that the Adaptive neural networks filter is suggested for de-noising the observations, specifically for the GPS displacement components of structures. Also, this model is expected to have significant influence on the design of structures in the low frequency responses and measurements’ contents. PMID:26402687
FPGA implementation of a stochastic neural network for monotonic pseudo-Boolean optimization.
Grossi, Giuliano; Pedersini, Federico
2008-08-01
In this paper a FPGA implementation of a novel neural stochastic model for solving constrained NP-hard problems is proposed and developed. The model exploits pseudo-Boolean functions both to express the constraints and to define the cost function, interpreted as energy of a neural network. A wide variety of NP-hard problems falls in the class of problems that can be solved by this model, particularly those having a quadratic pseudo-Boolean penalty function. The proposed hardware implementation provides high computation speed by exploiting parallelism, as the neuron update and the constraint violation check can be performed in parallel over the whole network. The neural system has been tested on random and benchmark graphs, showing good performance with respect to the same heuristic for the same problems. Furthermore, the computational speed of the FPGA implementation has been measured and compared to software implementation. The developed architecture featured dramatically faster computation, with respect to the software implementation, even adopting a low-cost FPGA chip.
Dumidu Wijayasekara; Milos Manic; Piyush Sabharwall; Vivek Utgikar
2011-07-01
Artificial Neural Networks (ANN) have been used in the past to predict the performance of printed circuit heat exchangers (PCHE) with satisfactory accuracy. Typically published literature has focused on optimizing ANN using a training dataset to train the network and a testing dataset to evaluate it. Although this may produce outputs that agree with experimental results, there is a risk of over-training or overlearning the network rather than generalizing it, which should be the ultimate goal. An over-trained network is able to produce good results with the training dataset but fails when new datasets with subtle changes are introduced. In this paper we present EBaLM-OTR (error back propagation and Levenberg-Marquardt algorithms for over training resilience) technique, which is based on a previously discussed method of selecting neural network architecture that uses a separate validation set to evaluate different network architectures based on mean square error (MSE), and standard deviation of MSE. The method uses k-fold cross validation. Therefore in order to select the optimal architecture for the problem, the dataset is divided into three parts which are used to train, validate and test each network architecture. Then each architecture is evaluated according to their generalization capability and capability to conform to original data. The method proved to be a comprehensive tool in identifying the weaknesses and advantages of different network architectures. The method also highlighted the fact that the architecture with the lowest training error is not always the most generalized and therefore not the optimal. Using the method the testing error achieved was in the order of magnitude of within 10{sup -5} - 10{sup -3}. It was also show that the absolute error achieved by EBaLM-OTR was an order of magnitude better than the lowest error achieved by EBaLM-THP.
NASA Astrophysics Data System (ADS)
Singh, B. B.
2016-12-01
India produces majority of its electricity from coal but a huge quantity of coal burns every day due to coal fires and also poses a threat to the environment as severe pollutants. In the present study we had demonstrated the usage of Neural Network based approach with an integrated Particle Swarm Optimization (PSO) inversion technique. The Self Potential (SP) data set is used for the early detection of coal fires. The study was conducted over the East Basuria colliery, Jharia Coal Field, Jharkhand, India. The causative source was modelled as an inclined sheet like anomaly and the synthetic data was generated. Neural Network scheme consists of an input layer, hidden layers and an output layer. The input layer corresponds to the SP data and the output layer is the estimated depth of the coal fire. A synthetic dataset was modelled with some of the known parameters such as depth, conductivity, inclination angle, half width etc. associated with causative body and gives a very low misfit error of 0.0032%. Therefore, the method was found accurate in predicting the depth of the source body. The technique was applied to the real data set and the model was trained until a very good correlation of determination `R2' value of 0.98 is obtained. The depth of the source body was found to be 12.34m with a misfit error percentage of 0.242%. The inversion results were compared with the lithologs obtained from a nearby well which corresponds to the L3 coal seam. The depth of the coal fire had exactly matched with the half width of the anomaly which suggests that the fire is widely spread. The inclination angle of the anomaly was 135.510 which resembles the development of the geometrically complex fracture planes. These fractures may be developed due to anisotropic weakness of the ground which acts as passage for the air. As a result coal fires spreads along these fracture planes. The results obtained from the Neural Network was compared with PSO inversion results and were found in
NASA Technical Reports Server (NTRS)
Leyland, Jane Anne
2001-01-01
Given the predicted growth in air transportation, the potential exists for significant market niches for rotary wing subsonic vehicles. Technological advances which optimise rotorcraft aeromechanical behaviour can contribute significantly to both their commercial and military development, acceptance, and sales. Examples of the optimisation of rotorcraft aeromechanical behaviour which are of interest include the minimisation of vibration and/or loads. The reduction of rotorcraft vibration and loads is an important means to extend the useful life of the vehicle and to improve its ride quality. Although vibration reduction can be accomplished by using passive dampers and/or tuned masses, active closed-loop control has the potential to reduce vibration and loads throughout a.wider flight regime whilst requiring less additional weight to the aircraft man that obtained by using passive methads. It is ernphasised that the analysis described herein is applicable to all those rotorcraft aeromechanical behaviour optimisation problems for which the relationship between the harmonic control vector and the measurement vector can be adequately described by a neural-network model.
NASA Astrophysics Data System (ADS)
Swain, Basudev; Mishra, Chinmayee; Kang, Leeseung; Park, Kyung-Soo; Lee, Chan Gi; Hong, Hyun Seon; Park, Jeung-Jin
2015-05-01
Recovery of metal values from GaN, a metal-organic chemical vapor deposition (MOCVD) waste of GaN based power device and LED industry is investigated by acidic leaching. Leaching kinetics of gallium rich MOCVD waste is studied and the process is optimized. The gallium rich waste MOCVD dust is characterized by XRD and ICP-AES analysis followed by aqua regia digestion. Different mineral acids are used to find out the best lixiviant for selective leaching of the gallium and indium. Concentrated HCl is relatively better lixiviant having reasonably faster kinetic and better leaching efficiency. Various leaching process parameters like effect of acidity, pulp density, temperature and concentration of catalyst on the leaching efficiency of gallium and indium are investigated. Reasonably, 4 M HCl, a pulp density of 50 g/L, 100 °C and stirring rate of 400 rpm are the effective optimum condition for quantitative leaching of gallium and indium.
Cheema, Jitender Jit Singh; Sankpal, Narendra V; Tambe, Sanjeev S; Kulkarni, Bhaskar D
2002-01-01
This article presents two hybrid strategies for the modeling and optimization of the glucose to gluconic acid batch bioprocess. In the hybrid approaches, first a novel artificial intelligence formalism, namely, genetic programming (GP), is used to develop a process model solely from the historic process input-output data. In the next step, the input space of the GP-based model, representing process operating conditions, is optimized using two stochastic optimization (SO) formalisms, viz., genetic algorithms (GAs) and simultaneous perturbation stochastic approximation (SPSA). These SO formalisms possess certain unique advantages over the commonly used gradient-based optimization techniques. The principal advantage of the GP-GA and GP-SPSA hybrid techniques is that process modeling and optimization can be performed exclusively from the process input-output data without invoking the detailed knowledge of the process phenomenology. The GP-GA and GP-SPSA techniques have been employed for modeling and optimization of the glucose to gluconic acid bioprocess, and the optimized process operating conditions obtained thereby have been compared with those obtained using two other hybrid modeling-optimization paradigms integrating artificial neural networks (ANNs) and GA/SPSA formalisms. Finally, the overall optimized operating conditions given by the GP-GA method, when verified experimentally resulted in a significant improvement in the gluconic acid yield. The hybrid strategies presented here are generic in nature and can be employed for modeling and optimization of a wide variety of batch and continuous bioprocesses.
NASA Astrophysics Data System (ADS)
Shkvarko, Yuriy, IV; Butenko, Sergiy
2006-05-01
We address a new approach to the problem of improvement of the quality of multi-grade spatial-spectral images provided by several remote sensing (RS) systems as required for environmental resource management with the use of multisource RS data. The problem of multi-spectral reconstructive imaging with multisource information fusion is stated and treated as an aggregated ill-conditioned inverse problem of reconstruction of a high-resolution image from the data provided by several sensor systems that employ the same or different image formation methods. The proposed fusionoptimization technique aggregates the experiment design regularization paradigm with neural-network-based implementation of the multisource information fusion method. The maximum entropy (ME) requirement and projection regularization constraints are posed as prior knowledge for fused reconstruction and the experiment-design regularization methodology is applied to perform the optimization of multisource information fusion. Computationally, the reconstruction and fusion are accomplished via minimization of the energy function of the proposed modified multistate Hopfield-type neural network (NN) that integrates the model parameters of all systems incorporating a priori information, aggregate multisource measurements and calibration data. The developed theory proves that the designed maximum entropy neural network (MENN) is able to solve the multisource fusion tasks without substantial complication of its computational structure independent on the number of systems to be fused. For each particular case, only the proper adjustment of the MENN's parameters (i.e. interconnection strengths and bias inputs) should be accomplished. Simulation examples are presented to illustrate the good overall performance of the fused reconstruction achieved with the developed MENN algorithm applied to the real-world multi-spectral environmental imagery.
Stability of discrete time recurrent neural networks and nonlinear optimization problems.
Singh, Jayant; Barabanov, Nikita
2016-02-01
We consider the method of Reduction of Dissipativity Domain to prove global Lyapunov stability of Discrete Time Recurrent Neural Networks. The standard and advanced criteria for Absolute Stability of these essentially nonlinear systems produce rather weak results. The method mentioned above is proved to be more powerful. It involves a multi-step procedure with maximization of special nonconvex functions over polytopes on every step. We derive conditions which guarantee an existence of at most one point of local maximum for such functions over every hyperplane. This nontrivial result is valid for wide range of neuron transfer functions. Copyright © 2015 Elsevier Ltd. All rights reserved.
Barmpalexis, Panagiotis; Kachrimanis, Kyriakos; Georgarakis, Emanouil
2011-01-01
The present study investigates the use of nimodipine-polyethylene glycol solid dispersions for the development of effervescent controlled release floating tablet formulations. The physical state of the dispersed nimodipine in the polymer matrix was characterized by differential scanning calorimetry, powder X-ray diffraction, FT-IR spectroscopy and polarized light microscopy, and the mixture proportions of polyethylene glycol (PEG), polyvinyl-pyrrolidone (PVP), hydroxypropylmethylcellulose (HPMC), effervescent agents (EFF) and nimodipine were optimized in relation to drug release (% release at 60 min, and time at which the 90% of the drug was dissolved) and floating properties (tablet's floating strength and duration), employing a 25-run D-optimal mixture design combined with artificial neural networks (ANNs) and genetic programming (GP). It was found that nimodipine exists as mod I microcrystals in the solid dispersions and is stable for at least a three-month period. The tablets showed good floating properties and controlled release profiles, with drug release proceeding via the concomitant operation of swelling and erosion of the polymer matrix. ANNs and GP both proved to be efficient tools in the optimization of the tablet formulation, and the global optimum formulation suggested by the GP equations consisted of PEG=9%, PVP=30%, HPMC=36%, EFF=11%, nimodipine=14%. Copyright © 2010 Elsevier B.V. All rights reserved.
Optimal fuel loading pattern design using an artificial neural network and a fuzzy rule-based system
Han Gon Kim; Soon Heung Chang; Byung Ho Lee )
1993-10-01
The Optimal Fuel Shuffling System (OFSS) was developed for the optimal design of pressurized water reactor (PWR) fuel loading patterns. An optimal loading pattern is defined in which the local power peaking factor is lower than a predetermined value during one cycle and the effective multiplication factor is maximized to extract the maximum energy. The OFSS is a hybrid system in which a rule-based system, fuzzy logic, and an artificial neural network (ANN) are connected with each other. The rule-based system classifies loading patterns into two types by using several heuristic rules and a fuzzy rule. The fuzzy rule is introduced to achieve a more effective and faster search. Its membership function is automatically updated in accordance with the prediction results. The ANN predicts core parameters for the patterns generated from the rule-based system. A back propagation network is used for fast prediction of the core parameters. The ANN and fuzzy logic can be used to improve the capabilities of existing algorithms. The OFSS was demonstrated and validated for cycle 1 of the Kori-1 PWR.
Sabes, Philip N
2011-01-01
Although multisensory integration has been well modeled at the behavioral level, the link between these behavioral models and the underlying neural circuits is still not clear. This gap is even greater for the problem of sensory integration during movement planning and execution. The difficulty lies in applying simple models of sensory integration to the complex computations that are required for movement control and to the large networks of brain areas that perform these computations. Here I review psychophysical, computational, and physiological work on multisensory integration during movement planning, with an emphasis on goal-directed reaching. I argue that sensory transformations must play a central role in any modeling effort. In particular, the statistical properties of these transformations factor heavily into the way in which downstream signals are combined. As a result, our models of optimal integration are only expected to apply "locally," that is, independently for each brain area. I suggest that local optimality can be reconciled with globally optimal behavior if one views the collection of parietal sensorimotor areas not as a set of task-specific domains, but rather as a palette of complex, sensorimotor representations that are flexibly combined to drive downstream activity and behavior.
Kasiri, M B; Aleboyeh, H; Aleboyeh, A
2008-11-01
In this study, estimation capacities of response surface methodology (RSM) and artificial neural network (ANN) in a heterogeneous photo-Fenton process were investigated. The zeolite Fe-ZSM5 was used as heterogeneous catalyst of the process for degradation of C.I. Acid Red 14 azo dye. The efficiency of the process was studied as a function of four independent variables, concentration of the catalyst, molar ratio of initial concentration of H2O2 to that of the dye (H value), initial concentration of the dye and initial pH of the solution. First, a central composite design (CCD) and response surface methodology were used to evaluate simple and combined effects of these parameters and to optimize process efficiency. Satisfactory prediction second-order regression was derived by RSM. Then, the independent parameters were fed as inputs to an artificial neural network while the output of the network was the degradation efficiency of the process. The multilayer feed-forward networks were trained by the sets of input-output patterns using a backpropagation algorithm. Comparable results were achieved for data fitting by using ANN and RSM. In both methods, the dye mineralization process was mainly influenced by pH and the initial concentration of the dye, whereas the other factors showed lower effects.
Ramos-Gómez, Milagros; Seiz, Emma G; Martínez-Serrano, Alberto
2015-03-05
Magnetic resonance imaging is the ideal modality for non-invasive in vivo cell tracking allowing for longitudinal studies over time. Cells labeled with superparamagnetic iron oxide nanoparticles have been shown to induce sufficient contrast for in vivo magnetic resonance imaging enabling the in vivo analysis of the final location of the transplanted cells. For magnetic nanoparticles to be useful, a high internalization efficiency of the particles is required without compromising cell function, as well as validation of the magnetic nanoparticles behaviour inside the cells. In this work, we report the development, optimization and validation of an efficient procedure to label human neural stem cells with commercial nanoparticles in the absence of transfection agents. Magnetic nanoparticles used here do not affect cell viability, cell morphology, cell differentiation or cell cycle dynamics. Moreover, human neural stem cells progeny labeled with magnetic nanoparticles are easily and non-invasively detected long time after transplantation in a rat model of Parkinson's disease (up to 5 months post-grafting) by magnetic resonance imaging. These findings support the use of commercial MNPs to track cells for short- and mid-term periods after transplantation for studies of brain cell replacement therapy. Nevertheless, long-term MR images should be interpreted with caution due to the possibility that some MNPs may be expelled from the transplanted cells and internalized by host microglial cells.
Hierarchical winner-take-all particle swarm optimization social network for neural model fitting.
Coventry, Brandon S; Parthasarathy, Aravindakshan; Sommer, Alexandra L; Bartlett, Edward L
2017-02-01
Particle swarm optimization (PSO) has gained widespread use as a general mathematical programming paradigm and seen use in a wide variety of optimization and machine learning problems. In this work, we introduce a new variant on the PSO social network and apply this method to the inverse problem of input parameter selection from recorded auditory neuron tuning curves. The topology of a PSO social network is a major contributor to optimization success. Here we propose a new social network which draws influence from winner-take-all coding found in visual cortical neurons. We show that the winner-take-all network performs exceptionally well on optimization problems with greater than 5 dimensions and runs at a lower iteration count as compared to other PSO topologies. Finally we show that this variant of PSO is able to recreate auditory frequency tuning curves and modulation transfer functions, making it a potentially useful tool for computational neuroscience models.
Kumar, K Jayaram; Panpalia, Gopal Mohan; Priyadarshini, Surabhi
2011-06-01
The purpose of this study was to optimize the concentration of a fatty alcohol, in addition to internal phase, for formulating a stable O/W emulsion, by using artificial neural networks (ANNs). Predictions from ANNs are accurate and allow quantification of the relative importance of the inputs. Furthermore, by varying the network topology and parameters it was possible to obtain output values that were close to experimental values. The ANN model's predictive results and the actual output values were compared. R(2) values depict the percentage of response variability for the model; R(2) value of 0.84 for the model suggested adequate modeling, which is supported by the correlation coefficient value of 0.9445.
NASA Astrophysics Data System (ADS)
Shan, Bonan; Wang, Jiang; Deng, Bin; Wei, Xile; Yu, Haitao; Zhang, Zhen; Li, Huiyan
2016-07-01
This paper proposes an epilepsy detection and closed-loop control strategy based on Particle Swarm Optimization (PSO) algorithm. The proposed strategy can effectively suppress the epileptic spikes in neural mass models, where the epileptiform spikes are recognized as the biomarkers of transitions from the normal (interictal) activity to the seizure (ictal) activity. In addition, the PSO algorithm shows capabilities of accurate estimation for the time evolution of key model parameters and practical detection for all the epileptic spikes. The estimation effects of unmeasurable parameters are improved significantly compared with unscented Kalman filter. When the estimated excitatory-inhibitory ratio exceeds a threshold value, the epileptiform spikes can be inhibited immediately by adopting the proportion-integration controller. Besides, numerical simulations are carried out to illustrate the effectiveness of the proposed method as well as the potential value for the model-based early seizure detection and closed-loop control treatment design.
López-Caraballo, C. H.; Lazzús, J. A.; Salfate, I.; Rojas, P.; Rivera, M.; Palma-Chilla, L.
2015-01-01
An artificial neural network (ANN) based on particle swarm optimization (PSO) was developed for the time series prediction. The hybrid ANN+PSO algorithm was applied on Mackey-Glass chaotic time series in the short-term x(t + 6). The performance prediction was evaluated and compared with other studies available in the literature. Also, we presented properties of the dynamical system via the study of chaotic behaviour obtained from the predicted time series. Next, the hybrid ANN+PSO algorithm was complemented with a Gaussian stochastic procedure (called stochastic hybrid ANN+PSO) in order to obtain a new estimator of the predictions, which also allowed us to compute the uncertainties of predictions for noisy Mackey-Glass chaotic time series. Thus, we studied the impact of noise for several cases with a white noise level (σN) from 0.01 to 0.1. PMID:26351449
NASA Astrophysics Data System (ADS)
Park, K.; Bayram, C.
2016-10-01
Here, we investigate the effects of thermal boundary resistance (TBR) and temperature-dependent thermal conductivity on the thermal resistance of GaN/substrate stacks. A combination of parameters such as substrates {diamond, silicon carbide, silicon, and sapphire}, thermal boundary resistance {10-60 m2K/GW}, heat source lengths {10 nm-20 μm}, and power dissipation levels {1-8 W} are studied by using technology computer-aided design (TCAD) software Synopsys. Among diamond, silicon carbide, silicon, and sapphire substrates, the diamond provides the lowest thermal resistance due to its superior thermal conductivity. We report that due to non-zero thermal boundary resistance and localized heating in GaN-based high electron mobility transistors, an optimum separation between the heat source and substrate exists. For high power (i.e., 8 W) heat dissipation on high thermal conductive substrates (i.e., diamond), the optimum separation between the heat source and substrate becomes submicron thick (i.e., 500 nm), which reduces the hotspot temperature as much as 50 °C compared to conventional multi-micron thick case (i.e., 4 μm). This is attributed to the thermal conductivity drop in GaN near the heat source. Improving the TBR between GaN and diamond increases temperature reduction by our further approach. Overall, we provide thermal management design guidelines for GaN-based devices.
Character Recognition Using Genetically Trained Neural Networks
Diniz, C.; Stantz, K.M.; Trahan, M.W.; Wagner, J.S.
1998-10-01
Computationally intelligent recognition of characters and symbols addresses a wide range of applications including foreign language translation and chemical formula identification. The combination of intelligent learning and optimization algorithms with layered neural structures offers powerful techniques for character recognition. These techniques were originally developed by Sandia National Laboratories for pattern and spectral analysis; however, their ability to optimize vast amounts of data make them ideal for character recognition. An adaptation of the Neural Network Designer soflsvare allows the user to create a neural network (NN_) trained by a genetic algorithm (GA) that correctly identifies multiple distinct characters. The initial successfid recognition of standard capital letters can be expanded to include chemical and mathematical symbols and alphabets of foreign languages, especially Arabic and Chinese. The FIN model constructed for this project uses a three layer feed-forward architecture. To facilitate the input of characters and symbols, a graphic user interface (GUI) has been developed to convert the traditional representation of each character or symbol to a bitmap. The 8 x 8 bitmap representations used for these tests are mapped onto the input nodes of the feed-forward neural network (FFNN) in a one-to-one correspondence. The input nodes feed forward into a hidden layer, and the hidden layer feeds into five output nodes correlated to possible character outcomes. During the training period the GA optimizes the weights of the NN until it can successfully recognize distinct characters. Systematic deviations from the base design test the network's range of applicability. Increasing capacity, the number of letters to be recognized, requires a nonlinear increase in the number of hidden layer neurodes. Optimal character recognition performance necessitates a minimum threshold for the number of cases when genetically training the net. And, the amount of
Wang, Jie-sheng; Han, Shuang; Shen, Na-na; Li, Shu-xia
2014-01-01
For meeting the forecasting target of key technology indicators in the flotation process, a BP neural network soft-sensor model based on features extraction of flotation froth images and optimized by shuffled cuckoo search algorithm is proposed. Based on the digital image processing technique, the color features in HSI color space, the visual features based on the gray level cooccurrence matrix, and the shape characteristics based on the geometric theory of flotation froth images are extracted, respectively, as the input variables of the proposed soft-sensor model. Then the isometric mapping method is used to reduce the input dimension, the network size, and learning time of BP neural network. Finally, a shuffled cuckoo search algorithm is adopted to optimize the BP neural network soft-sensor model. Simulation results show that the model has better generalization results and prediction accuracy.
Wang, Jie-sheng; Han, Shuang; Shen, Na-na; Li, Shu-xia
2014-01-01
For meeting the forecasting target of key technology indicators in the flotation process, a BP neural network soft-sensor model based on features extraction of flotation froth images and optimized by shuffled cuckoo search algorithm is proposed. Based on the digital image processing technique, the color features in HSI color space, the visual features based on the gray level cooccurrence matrix, and the shape characteristics based on the geometric theory of flotation froth images are extracted, respectively, as the input variables of the proposed soft-sensor model. Then the isometric mapping method is used to reduce the input dimension, the network size, and learning time of BP neural network. Finally, a shuffled cuckoo search algorithm is adopted to optimize the BP neural network soft-sensor model. Simulation results show that the model has better generalization results and prediction accuracy. PMID:25133210
Optimal linear compression under unreliable representation and robust PCA neural models.
Diamantaras, K I; Hornik, K; Strintzis, M G
1999-01-01
In a typical linear data compression system the representation variables resulting from the coding operation are assumed totally reliable and therefore the solution in the mean-squared-error sense is an orthogonal projector to the so-called principal component subspace. When the representation variables are contaminated by additive noise which is uncorrelated with the signal, the problem is called noisy principal component analysis (NPCA) and the optimal MSE solution is not a trivial extension of PCA. We first show that the problem is not well defined unless we impose explicit or implicit constraints on either the coding or the decoding operator. Second, orthogonality is not a property of the optimal solution under most constraints. Third, the signal components may or may not be reconstructed depending on the noise level. As the noise power increases, we observe rank reduction in the optimal solution under most reasonable constraints. In these cases it appears that it is preferable to omit the smaller signal components rather than attempting to reconstruct them. This phenomenon has similarities with classical information theoretical results, notably the water-filling analogy, found in parallel additive Gaussian noise channels. Finally, we show that standard Hebbian-type PCA learning algorithms are not optimally robust to noise, and propose a new Hebbian-type learning algorithm which is optimally robust in the NPCA sense.
Park, Jae -Cheol; Al-Jassim, Mowafak; Kim, Tae -Won
2017-02-01
Here, copper gallium selenide (CGS) thin films were fabricated using a combinatorial one-step sputtering process without an additional selenization process. The sample libraries as a function of vertical and lateral distance from the sputtering target were synthesized on a single soda-lime glass substrate at the substrate temperature of 500 °C employing a stoichiometric CGS single target. As we increased the vertical distance between the target and substrate, the CGS thin films had more stable and uniform characteristics in structural and chemical properties. Under the optimized conditions of the vertical distance (150 mm), the CGS thin films showed densely packed grainsmore » and large grain sizes up to 1 μm in scale with decreasing lateral distances. The composition ratio of Ga/[Cu+Ga] and Se/[Cu+Ga] showed 0.50 and 0.93, respectively, in nearly the same composition as the sputtering target. X-ray diffraction and Raman spectroscopy revealed that the CGS thin films had a pure chalcopyrite phase without any secondary phases such as Cu–Se or ordered vacancy compounds, respectively. In addition, we found that the optical bandgap energies of the CGS thin films are shifted from 1.650 to 1.664 eV with decreasing lateral distance, showing a near-stoichiometric region with chalcopyrite characteristics.« less
Paskiabi, Farnoush Asghari; Mirzaei, Esmaeil; Amani, Amir; Shokrgozar, Mohammad Ali; Saber, Reza; Faridi-Majidi, Reza
2015-11-01
This paper proposes an artificial neural networks approach to finding the effects of electrospinning parameters on alignment of poly(ɛ-caprolactone)/poly(glycolic acid) blend nanofibers. Four electrospinning parameters, namely total polymer concentration, working distance, drum speed and applied voltage were considered as input and the standard deviation of the angles of nanofibers, introducing fibers alignments, as the output of the model. The results demonstrated that drum speed and applied voltage are two critical factors influencing nanofibers alignment, however their effect are entirely interdependent. Their effects also are not independent of other electrospinning parameters. In obtaining aligned electrospun nanofibers, the concentration and working distance can also be effective. In vitro cell culture study on random and aligned nanofibers showed directional growth of cells on aligned fibers.
Simulation tests of the optimization method of Hopfield and Tank using neural networks
NASA Technical Reports Server (NTRS)
Paielli, Russell A.
1988-01-01
The method proposed by Hopfield and Tank for using the Hopfield neural network with continuous valued neurons to solve the traveling salesman problem is tested by simulation. Several researchers have apparently been unable to successfully repeat the numerical simulation documented by Hopfield and Tank. However, as suggested to the author by Adams, it appears that the reason for those difficulties is that a key parameter value is reported erroneously (by four orders of magnitude) in the original paper. When a reasonable value is used for that parameter, the network performs generally as claimed. Additionally, a new method of using feedback to control the input bias currents to the amplifiers is proposed and successfully tested. This eliminates the need to set the input currents by trial and error.
Smart-Pixel Array Processors Based on Optimal Cellular Neural Networks for Space Sensor Applications
NASA Technical Reports Server (NTRS)
Fang, Wai-Chi; Sheu, Bing J.; Venus, Holger; Sandau, Rainer
1997-01-01
A smart-pixel cellular neural network (CNN) with hardware annealing capability, digitally programmable synaptic weights, and multisensor parallel interface has been under development for advanced space sensor applications. The smart-pixel CNN architecture is a programmable multi-dimensional array of optoelectronic neurons which are locally connected with their local neurons and associated active-pixel sensors. Integration of the neuroprocessor in each processor node of a scalable multiprocessor system offers orders-of-magnitude computing performance enhancements for on-board real-time intelligent multisensor processing and control tasks of advanced small satellites. The smart-pixel CNN operation theory, architecture, design and implementation, and system applications are investigated in detail. The VLSI (Very Large Scale Integration) implementation feasibility was illustrated by a prototype smart-pixel 5x5 neuroprocessor array chip of active dimensions 1380 micron x 746 micron in a 2-micron CMOS technology.
Optimal system size for complex dynamics in random neural networks near criticality
Wainrib, Gilles; García del Molino, Luis Carlos
2013-12-15
In this article, we consider a model of dynamical agents coupled through a random connectivity matrix, as introduced by Sompolinsky et al. [Phys. Rev. Lett. 61(3), 259–262 (1988)] in the context of random neural networks. When system size is infinite, it is known that increasing the disorder parameter induces a phase transition leading to chaotic dynamics. We observe and investigate here a novel phenomenon in the sub-critical regime for finite size systems: the probability of observing complex dynamics is maximal for an intermediate system size when the disorder is close enough to criticality. We give a more general explanation of this type of system size resonance in the framework of extreme values theory for eigenvalues of random matrices.
Equivalent Neural Network Optimal Coefficients Using Forgetting Factor with Sliding Modes
2016-01-01
The Artificial Neural Network (ANN) concept is familiar in methods whose task is, for example, the identification or approximation of the outputs of complex systems difficult to model. In general, the objective is to determine online the adequate parameters to reach a better point-to-point convergence rate, so that this paper presents the parameter estimation for an equivalent ANN (EANN), obtaining a recursive identification for a stochastic system, firstly, with constant parameters and, secondly, with nonstationary output system conditions. Therefore, in the last estimation, the parameters also have stochastic properties, making the traditional approximation methods not adequate due to their losing of convergence rate. In order to give a solution to this problematic, we propose a nonconstant exponential forgetting factor (NCEFF) with sliding modes, obtaining in almost all points an exponential convergence rate decreasing. Theoretical results of both identification stages are performed using MATLAB® and compared, observing improvement when the new proposal for nonstationary output conditions is applied. PMID:28058045
Equivalent Neural Network Optimal Coefficients Using Forgetting Factor with Sliding Modes.
Aguilar Cruz, Karen Alicia; Medel Juárez, José de Jesús; Urbieta Parrazales, Romeo
2016-01-01
The Artificial Neural Network (ANN) concept is familiar in methods whose task is, for example, the identification or approximation of the outputs of complex systems difficult to model. In general, the objective is to determine online the adequate parameters to reach a better point-to-point convergence rate, so that this paper presents the parameter estimation for an equivalent ANN (EANN), obtaining a recursive identification for a stochastic system, firstly, with constant parameters and, secondly, with nonstationary output system conditions. Therefore, in the last estimation, the parameters also have stochastic properties, making the traditional approximation methods not adequate due to their losing of convergence rate. In order to give a solution to this problematic, we propose a nonconstant exponential forgetting factor (NCEFF) with sliding modes, obtaining in almost all points an exponential convergence rate decreasing. Theoretical results of both identification stages are performed using MATLAB® and compared, observing improvement when the new proposal for nonstationary output conditions is applied.
Optimal system size for complex dynamics in random neural networks near criticality
Wainrib, Gilles; García del Molino, Luis Carlos
2013-12-15
In this article, we consider a model of dynamical agents coupled through a random connectivity matrix, as introduced by Sompolinsky et al. [Phys. Rev. Lett. 61(3), 259–262 (1988)] in the context of random neural networks. When system size is infinite, it is known that increasing the disorder parameter induces a phase transition leading to chaotic dynamics. We observe and investigate here a novel phenomenon in the sub-critical regime for finite size systems: the probability of observing complex dynamics is maximal for an intermediate system size when the disorder is close enough to criticality. We give a more general explanation of this type of system size resonance in the framework of extreme values theory for eigenvalues of random matrices.
Smart-Pixel Array Processors Based on Optimal Cellular Neural Networks for Space Sensor Applications
NASA Technical Reports Server (NTRS)
Fang, Wai-Chi; Sheu, Bing J.; Venus, Holger; Sandau, Rainer
1997-01-01
A smart-pixel cellular neural network (CNN) with hardware annealing capability, digitally programmable synaptic weights, and multisensor parallel interface has been under development for advanced space sensor applications. The smart-pixel CNN architecture is a programmable multi-dimensional array of optoelectronic neurons which are locally connected with their local neurons and associated active-pixel sensors. Integration of the neuroprocessor in each processor node of a scalable multiprocessor system offers orders-of-magnitude computing performance enhancements for on-board real-time intelligent multisensor processing and control tasks of advanced small satellites. The smart-pixel CNN operation theory, architecture, design and implementation, and system applications are investigated in detail. The VLSI (Very Large Scale Integration) implementation feasibility was illustrated by a prototype smart-pixel 5x5 neuroprocessor array chip of active dimensions 1380 micron x 746 micron in a 2-micron CMOS technology.
An optimization method for speech enhancement based on deep neural network
NASA Astrophysics Data System (ADS)
Sun, Haixia; Li, Sikun
2017-06-01
Now, this document puts forward a deep neural network (DNN) model with more credible data set and more robust structure. First, we take two regularization skills, dropout and sparsity constraint to strengthen the generalization ability of the model. In this way, not only the model is able to reach the consistency between the pre-training model and the fine-tuning model, but also it reduce resource consumption. Then network compression by weights sharing and quantization is allowed to reduce storage cost. In the end, we evaluate the quality of the reconstructed speech according to different criterion. The result proofs that the improved framework has good performance on speech enhancement and meets the requirement of speech processing.
Ground-based telescope pointing and tracking optimization using a neural controller.
Mancini, D; Brescia, M; Schipani, P
2003-01-01
Neural network models (NN) have emerged as important components for applications of adaptive control theories. Their basic generalization capability, based on acquired knowledge, together with execution rapidity and correlation ability between input stimula, are basic attributes to consider NN as an extremely powerful tool for on-line control of complex systems. By a control system point of view, not only accuracy and speed, but also, in some cases, a high level of adaptation capability is required in order to match all working phases of the whole system during its lifetime. This is particularly remarkable for a new generation ground-based telescope control system. Infact, strong changes in terms of system speed and instantaneous position error tolerance are necessary, especially in case of trajectory disturb induced by wind shake. The classical control scheme adopted in such a system is based on the proportional integral (PI) filter, already applied and implemented on a large amount of new generation telescopes, considered as a standard in this technological environment. In this paper we introduce the concept of a new approach, the neural variable structure proportional integral, (NVSPI), related to the implementation of a standard multi layer perceptron network in new generation ground-based Alt-Az telescope control systems. Its main purpose is to improve adaptive capability of the Variable structure proportional integral model, an already innovative control scheme recently introduced by authors [Proc SPIE (1997)], based on a modified version of classical PI control model, in terms of flexibility and accuracy of the dynamic response range also in presence of wind noise effects. The realization of a powerful well tested and validated telescope model simulation system allowed the possibility to directly compare performances of the two control schemes on simulated tracking trajectories, revealing extremely encouraging results in terms of NVSPI control robustness and
NASA Astrophysics Data System (ADS)
Kuo, Chin-chen
This thesis describes methods for improving the performance of poly(3,4-ethylenedioxythiophene) (PEDOT) as a direct neural interfacing material. The chronic foreign body response is always a challenge for implanted bionic devices. After long-term implantation (typically 2-4 weeks), insulating glial scars form around the devices, inhibiting signal transmission, which ultimately leads to device failure. The mechanical mismatch at the device-tissue interface is one of the issues that has been associated with chronic foreign body response. Another challenge for using PEDOT as a neural interface material is its mechanical failure after implantation. We observed cracking and delamination of PEDOT coatings on devices after extended implantations. In the first part of this thesis, we present a novel method for directly measuring the mechanical properties of a PEDOT thin film. Before investigating methods to improve the mechanical behavior of PEDOT, a comprehensive understanding of the mechanical properties of PEDOT thin film is required. A PEDOT thin film was machined into a dog-bone shape specimen with a dual beam FIB-SEM. With an OmniProbe, this PEDOT specimen could be attached onto a force sensor, while the other side was attached to OmniProbe. By moving the OmniProbe, the specimen could be deformed in tension, and a force sensor recorded the applied load on the sample simultaneously. Mechanical tensile tests were conducted in the FIB-SEM chamber along with in situ observation. With precise force measurement from the force sensor and the corresponding high resolution SEM images, we were able to convert the data to a stress-strain curve for further analysis. By analyzing these stress-strain curves, we were able to obtain information about PEDOT including the Young's modulus, strength of failure, strain to failure, and toughness (energy to failure). This information should be useful for future material selection and molecular design for specific applications. The second
NASA Astrophysics Data System (ADS)
Abdollahi, Azita; Shams, Mehrzad; Abdollahi, Anita
2017-07-01
One of methods available to increase the rate of heat transfer in channels with parallel plates is making grooves in them. But, the fundamental problem of this method is the formation of stagnation zone in the grooves and as a result formation a zone with low energy transfer. In this paper, the effect of placing curved deflectors (geometries with elliptical forms) in channel on thermal and hydraulic characteristic of the fluid flow- with the aim of directing of the flow into the grooves and as a result increasing the rate of heat transfer in this zone- are investigated and heat transfer coefficient and pressure drop are calculated for different values of Reynolds number and geometrical parameters of the deflector (its small and large radiuses). The results show that the presence of the deflector in the channel significantly increases the heat transfer rate compare to the channel without deflector. Of course, it should be noted that this work also increases the pressure drop. So, finally in order to determine configurations of the deflector causing minimum pressure drop, maximum Nusselt number or a balance between them, optimization algorithm consisting of artificial neural network and multi-objective genetic algorithm was utilized to calculate the optimal values of these parameters.
Moteghaed, Niloofar Yousefi; Maghooli, Keivan; Pirhadi, Shiva; Garshasbi, Masoud
2015-01-01
The improvement of high-through-put gene profiling based microarrays technology has provided monitoring the expression value of thousands of genes simultaneously. Detailed examination of changes in expression levels of genes can help physicians to have efficient diagnosing, classification of tumors and cancer's types as well as effective treatments. Finding genes that can classify the group of cancers correctly based on hybrid optimization algorithms is the main purpose of this paper. In this paper, a hybrid particle swarm optimization and genetic algorithm method are used for gene selection and also artificial neural network (ANN) is adopted as the classifier. In this work, we have improved the ability of the algorithm for the classification problem by finding small group of biomarkers and also best parameters of the classifier. The proposed approach is tested on three benchmark gene expression data sets: Blood (acute myeloid leukemia, acute lymphoblastic leukemia), colon and breast datasets. We used 10-fold cross-validation to achieve accuracy and also decision tree algorithm to find the relation between the biomarkers for biological point of view. To test the ability of the trained ANN models to categorize the cancers, we analyzed additional blinded samples that were not previously used for the training procedure. Experimental results show that the proposed method can reduce the dimension of the data set and confirm the most informative gene subset and improve classification accuracy with best parameters based on datasets.
Zaki, Mohammad Reza; Varshosaz, Jaleh; Fathi, Milad
2015-05-20
Multivariate nature of drug loaded nanospheres manufacturing in term of multiplicity of involved factors makes it a time consuming and expensive process. In this study genetic algorithm (GA) and artificial neural network (ANN), two tools inspired by natural process, were employed to optimize and simulate the manufacturing process of agar nanospheres. The efficiency of GA was evaluated against the response surface methodology (RSM). The studied responses included particle size, poly dispersity index, zeta potential, drug loading and release efficiency. GA predicted greater extremum values for response factors compared to RSM. However, real values showed some deviations from predicted data. Appropriate agreement was found between ANN model predicted and real values for all five response factors with high correlation coefficients. GA was more successful than RSM in optimization and along with ANN were efficient tools in optimizing and modeling the fabrication process of drug loaded in agar nanospheres.
Singh, Sagar; Lo, Meng-Chen; Damodaran, Vinod B.; Kaplan, Hilton M.; Kohn, Joachim; Zahn, Jeffrey D.; Shreiber, David I.
2016-01-01
Single-unit recording neural probes have significant advantages towards improving signal-to-noise ratio and specificity for signal acquisition in brain-to-computer interface devices. Long-term effectiveness is unfortunately limited by the chronic injury response, which has been linked to the mechanical mismatch between rigid probes and compliant brain tissue. Small, flexible microelectrodes may overcome this limitation, but insertion of these probes without buckling requires supporting elements such as a stiff coating with a biodegradable polymer. For these coated probes, there is a design trade-off between the potential for successful insertion into brain tissue and the degree of trauma generated by the insertion. The objective of this study was to develop and validate a finite element model (FEM) to simulate insertion of coated neural probes of varying dimensions and material properties into brain tissue. Simulations were performed to predict the buckling and insertion forces during insertion of coated probes into a tissue phantom with material properties of brain. The simulations were validated with parallel experimental studies where probes were inserted into agarose tissue phantom, ex vivo chick embryonic brain tissue, and ex vivo rat brain tissue. Experiments were performed with uncoated copper wire and both uncoated and coated SU-8 photoresist and Parylene C probes. Model predictions were found to strongly agree with experimental results (<10% error). The ratio of the predicted buckling force-to-predicted insertion force, where a value greater than one would ideally be expected to result in successful insertion, was plotted against the actual success rate from experiments. A sigmoidal relationship was observed, with a ratio of 1.35 corresponding to equal probability of insertion and failure, and a ratio of 3.5 corresponding to a 100% success rate. This ratio was dubbed the “safety factor”, as it indicated the degree to which the coating should be over
Robust/optimal temperature profile control of a high-speed aerospace vehicle using neural networks.
Yadav, Vivek; Padhi, Radhakant; Balakrishnan, S N
2007-07-01
An approximate dynamic programming (ADP)-based suboptimal neurocontroller to obtain desired temperature for a high-speed aerospace vehicle is synthesized in this paper. A 1-D distributed parameter model of a fin is developed from basic thermal physics principles. "Snapshot" solutions of the dynamics are generated with a simple dynamic inversion-based feedback controller. Empirical basis functions are designed using the "proper orthogonal decomposition" (POD) technique and the snapshot solutions. A low-order nonlinear lumped parameter system to characterize the infinite dimensional system is obtained by carrying out a Galerkin projection. An ADP-based neurocontroller with a dual heuristic programming (DHP) formulation is obtained with a single-network-adaptive-critic (SNAC) controller for this approximate nonlinear model. Actual control in the original domain is calculated with the same POD basis functions through a reverse mapping. Further contribution of this paper includes development of an online robust neurocontroller to account for unmodeled dynamics and parametric uncertainties inherent in such a complex dynamic system. A neural network (NN) weight update rule that guarantees boundedness of the weights and relaxes the need for persistence of excitation (PE) condition is presented. Simulation studies show that in a fairly extensive but compact domain, any desired temperature profile can be achieved starting from any initial temperature profile. Therefore, the ADP and NN-based controllers appear to have the potential to become controller synthesis tools for nonlinear distributed parameter systems.
Pires, J C M; Gonçalves, B; Azevedo, F G; Carneiro, A P; Rego, N; Assembleia, A J B; Lima, J F B; Silva, P A; Alves, C; Martins, F G
2012-09-01
This study proposes three methodologies to define artificial neural network models through genetic algorithms (GAs) to predict the next-day hourly average surface ozone (O(3)) concentrations. GAs were applied to define the activation function in hidden layer and the number of hidden neurons. Two of the methodologies define threshold models, which assume that the behaviour of the dependent variable (O(3) concentrations) changes when it enters in a different regime (two and four regimes were considered in this study). The change from one regime to another depends on a specific value (threshold value) of an explanatory variable (threshold variable), which is also defined by GAs. The predictor variables were the hourly average concentrations of carbon monoxide (CO), nitrogen oxide, nitrogen dioxide (NO(2)), and O(3) (recorded in the previous day at an urban site with traffic influence) and also meteorological data (hourly averages of temperature, solar radiation, relative humidity and wind speed). The study was performed for the period from May to August 2004. Several models were achieved and only the best model of each methodology was analysed. In threshold models, the variables selected by GAs to define the O(3) regimes were temperature, CO and NO(2) concentrations, due to their importance in O(3) chemistry in an urban atmosphere. In the prediction of O(3) concentrations, the threshold model that considers two regimes was the one that fitted the data most efficiently.
NASA Astrophysics Data System (ADS)
Hess, A. E.; Capadona, J. R.; Shanmuganathan, K.; Hsu, L.; Rowan, S. J.; Weder, C.; Tyler, D. J.; Zorman, C. A.
2011-05-01
This paper reports the development of micromachining processes and mechanical evaluation of a stimuli-responsive, mechanically dynamic polymer nanocomposite for biomedical microsystems. This nanocomposite consists of a cellulose nanofiber network encased in a polyvinyl acetate matrix. Micromachined tensile testing structures fabricated from the nanocomposite displayed a reversible and switchable stiffness comparable to bulk samples, with a Young's modulus of 3420 MPa when dry, reducing to ~20 MPa when wet, and a stiff-to-flexible transition time of ~300 s. This mechanically dynamic behavior is particularly attractive for the development of adaptive intracortical probes that are sufficiently stiff to insert into the brain without buckling, but become highly compliant upon insertion. Along these lines, a micromachined neural probe incorporating parylene insulating/moisture barrier layers and Ti/Au electrodes was fabricated from the nanocomposite using a fabrication process designed specifically for this chemical- and temperature-sensitive material. It was found that the parylene layers only slightly increased the stiffness of the probe in the wet state in spite of its much higher Young's modulus. Furthermore, the Ti/Au electrodes exhibited impedance comparable to Au electrodes on conventional substrates. Swelling of the nanocomposite was highly anisotropic favoring the thickness dimension by a factor of 8 to 12, leading to excellent adhesion between the nanocomposite and parylene layers and no discernable deformation of the probes when deployed in deionized water.
Optimization of a GCaMP calcium indicator for neural activity imaging.
Akerboom, Jasper; Chen, Tsai-Wen; Wardill, Trevor J; Tian, Lin; Marvin, Jonathan S; Mutlu, Sevinç; Calderón, Nicole Carreras; Esposti, Federico; Borghuis, Bart G; Sun, Xiaonan Richard; Gordus, Andrew; Orger, Michael B; Portugues, Ruben; Engert, Florian; Macklin, John J; Filosa, Alessandro; Aggarwal, Aman; Kerr, Rex A; Takagi, Ryousuke; Kracun, Sebastian; Shigetomi, Eiji; Khakh, Baljit S; Baier, Herwig; Lagnado, Leon; Wang, Samuel S-H; Bargmann, Cornelia I; Kimmel, Bruce E; Jayaraman, Vivek; Svoboda, Karel; Kim, Douglas S; Schreiter, Eric R; Looger, Loren L
2012-10-03
Genetically encoded calcium indicators (GECIs) are powerful tools for systems neuroscience. Recent efforts in protein engineering have significantly increased the performance of GECIs. The state-of-the art single-wavelength GECI, GCaMP3, has been deployed in a number of model organisms and can reliably detect three or more action potentials in short bursts in several systems in vivo. Through protein structure determination, targeted mutagenesis, high-throughput screening, and a battery of in vitro assays, we have increased the dynamic range of GCaMP3 by severalfold, creating a family of "GCaMP5" sensors. We tested GCaMP5s in several systems: cultured neurons and astrocytes, mouse retina, and in vivo in Caenorhabditis chemosensory neurons, Drosophila larval neuromuscular junction and adult antennal lobe, zebrafish retina and tectum, and mouse visual cortex. Signal-to-noise ratio was improved by at least 2- to 3-fold. In the visual cortex, two GCaMP5 variants detected twice as many visual stimulus-responsive cells as GCaMP3. By combining in vivo imaging with electrophysiology we show that GCaMP5 fluorescence provides a more reliable measure of neuronal activity than its predecessor GCaMP3. GCaMP5 allows more sensitive detection of neural activity in vivo and may find widespread applications for cellular imaging in general.
Gutova, Margarita; Goldstein, Leanne; Metz, Marianne; Hovsepyan, Anahit; Tsurkan, Lyudmila G; Tirughana, Revathiswari; Tsaturyan, Lusine; Annala, Alexander J; Synold, Timothy W; Wan, Zesheng; Seeger, Robert; Anderson, Clarke; Moats, Rex A; Potter, Philip M; Aboody, Karen S
2017-03-17
Despite improved survival for children with newly diagnosed neuroblastoma (NB), recurrent disease is a significant problem, with treatment options limited by anti-tumor efficacy, patient drug tolerance, and cumulative toxicity. We previously demonstrated that neural stem cells (NSCs) expressing a modified rabbit carboxylesterase (rCE) can distribute to metastatic NB tumor foci in multiple organs in mice and convert the prodrug irinotecan (CPT-11) to the 1,000-fold more toxic topoisomerase-1 inhibitor SN-38, resulting in significant therapeutic efficacy. We sought to extend these studies by using a clinically relevant NSC line expressing a modified human CE (hCE1m6-NSCs) to establish proof of concept and identify an intravenous dose and treatment schedule that gave maximal efficacy. Human-derived NB cell lines were significantly more sensitive to treatment with hCE1m6-NSCs and irinotecan as compared with drug alone. This was supported by pharmacokinetic studies in subcutaneous NB mouse models demonstrating tumor-specific conversion of irinotecan to SN-38. Furthermore, NB-bearing mice that received repeat treatment with intravenous hCE1m6-NSCs and irinotecan showed significantly lower tumor burden (1.4-fold, p = 0.0093) and increased long-term survival compared with mice treated with drug alone. These studies support the continued development of NSC-mediated gene therapy for improved clinical outcome in NB patients.
Optimization of a GCaMP calcium indicator for neural activity imaging
Akerboom, Jasper; Chen, Tsai-Wen; Wardill, Trevor J.; Tian, Lin; Marvin, Jonathan S.; Mutlu, Sevinç; Calderón, Nicole Carreras; Esposti, Federico; Borghuis, Bart G.; Sun, Xiaonan Richard; Gordus, Andrew; Orger, Michael B.; Portugues, Ruben; Engert, Florian; Macklin, John J.; Filosa, Alessandro; Aggarwal, Aman; Kerr, Rex; Takagi, Ryousuke; Kracun, Sebastian; Shigetomi, Eiji; Khakh, Baljit S.; Baier, Herwig; Lagnado, Leon; Wang, Samuel S.-H.; Bargmann, Cornelia I.; Kimmel, Bruce E.; Jayaraman, Vivek; Svoboda, Karel; Kim, Douglas S.; Schreiter, Eric R.; Looger, Loren L.
2012-01-01
Genetically encoded calcium indicators (GECIs) are powerful tools for systems neuroscience. Recent efforts in protein engineering have significantly increased the performance of GECIs. The state-of-the art single-wavelength GECI, GCaMP3, has been deployed in a number of model organisms and can reliably detect three or more action potentials (APs) in short bursts in several systems in vivo. Through protein structure determination, targeted mutagenesis, high-throughput screening, and a battery of in vitro assays, we have increased the dynamic range of GCaMP3 by several-fold, creating a family of “GCaMP5” sensors. We tested GCaMP5s in several systems: cultured neurons and astrocytes, mouse retina, and in vivo in Caenorhabditis chemosensory neurons, Drosophila larval neuromuscular junction and adult antennal lobe, zebrafish retina and tectum, and mouse visual cortex. Signal-to-noise ratio was improved by at least 2–3-fold. In the visual cortex, two GCaMP5 variants detected twice as many visual stimulus-responsive cells as GCaMP3. By combining in vivo imaging with electrophysiology we show that GCaMP5 fluorescence provides a more reliable measure of neuronal activity than its predecessor GCaMP3. GCaMP5 allows more sensitive detection of neural activity in vivo and may find widespread applications for cellular imaging in general. PMID:23035093
Rivera, José; Carrillo, Mariano; Chacón, Mario; Herrera, Gilberto; Bojorquez, Gilberto
2007-01-01
The development of smart sensors involves the design of reconfigurable systems capable of working with different input sensors. Reconfigurable systems ideally should spend the least possible amount of time in their calibration. An autocalibration algorithm for intelligent sensors should be able to fix major problems such as offset, variation of gain and lack of linearity, as accurately as possible. This paper describes a new autocalibration methodology for nonlinear intelligent sensors based on artificial neural networks, ANN. The methodology involves analysis of several network topologies and training algorithms. The proposed method was compared against the piecewise and polynomial linearization methods. Method comparison was achieved using different number of calibration points, and several nonlinear levels of the input signal. This paper also shows that the proposed method turned out to have a better overall accuracy than the other two methods. Besides, experimentation results and analysis of the complete study, the paper describes the implementation of the ANN in a microcontroller unit, MCU. In order to illustrate the method capability to build autocalibration and reconfigurable systems, a temperature measurement system was designed and tested. The proposed method is an improvement over the classic autocalibration methodologies, because it impacts on the design process of intelligent sensors, autocalibration methodologies and their associated factors, like time and cost.
NASA Astrophysics Data System (ADS)
Vafaei, Masoud; Afrand, Masoud; Sina, Nima; Kalbasi, Rasool; Sourani, Forough; Teimouri, Hamid
2017-01-01
In this paper, the thermal conductivity ratio of MgO-MWCNTs/EG hybrid nanofluids has been predicted by an optimal artificial neural network at solid volume fractions of 0.05%, 0.1%, 0.15%, 0.2%, 0.4% and 0.6% in the temperature range of 25-50 °C. In this way, at the first, thirty six experimental data was presented to determine the thermal conductivity ratio of the hybrid nanofluid. Then, four optimal artificial neural networks with 6, 8, 10 and 12 neurons in hidden layer were designed to predict the thermal conductivity ratio of the nanofluid. The comparison between four optimal ANN results and experimental showed that the ANN with 12 neurons in hidden layer was the best model. Moreover, the results obtained from the best ANN indicated the maximum deviation margin of 0.8%.
Kalderstam, Jonas; Edén, Patrik; Ohlsson, Mattias
2015-01-01
We investigate a new method to place patients into risk groups in censored survival data. Properties such as median survival time, and end survival rate, are implicitly improved by optimizing the area under the survival curve. Artificial neural networks (ANN) are trained to either maximize or minimize this area using a genetic algorithm, and combined into an ensemble to predict one of low, intermediate, or high risk groups. Estimated patient risk can influence treatment choices, and is important for study stratification. A common approach is to sort the patients according to a prognostic index and then group them along the quartile limits. The Cox proportional hazards model (Cox) is one example of this approach. Another method of doing risk grouping is recursive partitioning (Rpart), which constructs a decision tree where each branch point maximizes the statistical separation between the groups. ANN, Cox, and Rpart are compared on five publicly available data sets with varying properties. Cross-validation, as well as separate test sets, are used to validate the models. Results on the test sets show comparable performance, except for the smallest data set where Rpart’s predicted risk groups turn out to be inverted, an example of crossing survival curves. Cross-validation shows that all three models exhibit crossing of some survival curves on this small data set but that the ANN model manages the best separation of groups in terms of median survival time before such crossings. The conclusion is that optimizing the area under the survival curve is a viable approach to identify risk groups. Training ANNs to optimize this area combines two key strengths from both prognostic indices and Rpart. First, a desired minimum group size can be specified, as for a prognostic index. Second, the ability to utilize non-linear effects among the covariates, which Rpart is also able to do. PMID:26352405