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? PMID:22230636
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.
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.
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.
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.
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…
Application of neural nets in structural optimization
NASA Technical Reports Server (NTRS)
Berke, Laszlo; Hajela, Prabhat
1993-01-01
The biological motivation for Artificial Neural Net developments is briefly discussed, and the most popular paradigm, the feedforward supervised learning net with error back propagation training algorithm, is introduced. Possible approaches for utilization in structural optimization is illustrated through simple examples. Other currently ongoing developments for application in structural mechanics are also mentioned.
Network dissection of neural networks used in optimal groundwater remediation
Rogers, L.L.; Johnson, V.M.; Dowla, F.U.
1992-12-01
We have been using an innovative computational approach for optimal groundwater management which involves use of artificial neural networks (ANNs) and the genetic algorithm (GA). In this approach, the ANN is trained to predict a particular aspect of the outcome of the flow and transport simulation. Then the.GA directs a search, based on the mechanics of genetics and natural selection, through possible management solutions, in this case patterns or realizations of pumping. These pumping realizations are presented to the trained ANN which predicts the outcome of the pumping realizations. The primary advantages of the ANN approach are parallel processing for the flow and transport simulations and the ability to ``recycle`` or reuse the base of knowledge formed by these flow and transport simulations.
Network dissection of neural networks used in optimal groundwater remediation
Rogers, L.L.; Johnson, V.M.; Dowla, F.U.
1992-12-01
We have been using an innovative computational approach for optimal groundwater management which involves use of artificial neural networks (ANNs) and the genetic algorithm (GA). In this approach, the ANN is trained to predict a particular aspect of the outcome of the flow and transport simulation. Then the.GA directs a search, based on the mechanics of genetics and natural selection, through possible management solutions, in this case patterns or realizations of pumping. These pumping realizations are presented to the trained ANN which predicts the outcome of the pumping realizations. The primary advantages of the ANN approach are parallel processing for the flow and transport simulations and the ability to recycle'' or reuse the base of knowledge formed by these flow and transport simulations.
Neural network training with global optimization techniques.
Yamazaki, Akio; Ludermir, Teresa B
2003-04-01
This paper presents an approach of using Simulated Annealing and Tabu Search for the simultaneous optimization of neural network architectures and weights. The problem considered is the odor recognition in an artificial nose. Both methods have produced networks with high classification performance and low complexity. Generalization has been improved by using the backpropagation algorithm for fine tuning. The combination of simple and traditional search methods has shown to be very suitable for generating compact and efficient networks. PMID:12923920
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
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.
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. PMID:25873990
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
Oil formation volume factor modeling: Traditional vs. Stochastically optimized neural networks
NASA Astrophysics Data System (ADS)
Bagheripour, Parisa; Asoodeh, Mojtaba; Asoodeh, Ali
2013-12-01
Oil formation volume factor (FVF) is considered as relative change in oil volume between reservoir condition and standard surface condition. FVF, always greater than one, is dominated by reservoir temperature, amount of dissolved gas in oil, and specific gravity of oil and dissolved gas. In addition to limitations on reliable sampling, experimental determination of FVF is associated with high costs and time-consumption. Therefore, this study proposes a novel approach based on hybrid genetic algorithm-pattern search (GA-PS) optimized neural network (NN) for fast, accurate, and cheap determination of oil FVF from available measured pressure-volume-temperature (PVT) data. Contrasting to traditional neural network which is in danger of sticking in local minima, GA-PS optimized NN is in charge of escaping from local minima and converging to global minimum. A group of 342 data points were used for model construction and a group of 219 data points were employed for model assessment. Results indicated superiority of GA-PS optimized NN to traditional NN. Oil FVF values, determined by GA-PS optimized NN were in good agreement with reality.
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
Genetic Algorithm Based Neural Networks for Nonlinear Optimization
Energy Science and Technology Software Center (ESTSC)
1994-09-28
This software develops a novel approach to nonlinear optimization using genetic algorithm based neural networks. To our best knowledge, this approach represents the first attempt at applying both neural network and genetic algorithm techniques to solve a nonlinear optimization problem. The approach constructs a neural network structure and an appropriately shaped energy surface whose minima correspond to optimal solutions of the problem. A genetic algorithm is employed to perform a parallel and powerful search ofmore » the energy surface.« less
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
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.
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).
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.
Modeling of CMM dynamic error based on optimization of neural network using genetic algorithm
NASA Astrophysics Data System (ADS)
Ying, Qu; Zai, Luo; Yi, Lu
2010-08-01
By analyzing the dynamic error of CMM, a model is established using BP neural network for CMM .The most important 5 input parameters which affect the dynamic error of CMM are approximate rate, length of rod, diameter of probe, coordinate values of X and coordinate values of Y. But the training of BP neural network can be easily trapped in local minimums and its training speed is slow. In order to overcome these disadvantages, genetic algorithm (GA) is introduced for optimization. So the model of GA-BP network is built up. In order to verify the model, experiments are done on the CMM of type 9158. Experimental results indicate that the entire optimizing capability of genetic algorithm is perfect. Compared with traditional BP network, the GA-BP network has better accuracy and adaptability and the training time is halved using GA-BP network. The average dynamic error can be reduced from 3.5μm to 0.7μm. So the precision is improved by 76%.
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. PMID:16278942
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
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
Optimization neural network for solving flow problems.
Perfetti, R
1995-01-01
This paper describes a neural network for solving flow problems, which are of interest in many areas of application as in fuel, hydro, and electric power scheduling. The neural network consist of two layers: a hidden layer and an output layer. The hidden units correspond to the nodes of the flow graph. The output units represent the branch variables. The network has a linear order of complexity, it is easily programmable, and it is suited for analog very large scale integration (VLSI) realization. The functionality of the proposed network is illustrated by a simulation example concerning the maximal flow problem. PMID:18263420
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
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.
GA-Based Image Restoration by Isophote Constraint Optimization
NASA Astrophysics Data System (ADS)
Kim, Jong Bae; Kim, Hang Joon
2003-12-01
We propose an efficient technique for image restoration based on a genetic algorithm (GA) with an isophote constraint. In our technique, the image restoration problem is modeled as an optimization problem which, in our case, is solved by a cost function with isophote constraint that is minimized using a GA. We consider that an image is decomposed into isophotes based on connected components of constant intensity. The technique creates an optimal connection of all pairs of isophotes disconnected by a caption in the frame. For connecting the disconnected isophotes, we estimate the value of the smoothness, given by the best chromosomes of the GA and project this value in the isophote direction. Experimental results show a great possibility for automatic restoration of a region in an advertisement scene.
Applying neural networks to optimize instrumentation performance
Start, S.E.; Peters, G.G.
1995-06-01
Well calibrated instrumentation is essential in providing meaningful information about the status of a plant. Signals from plant instrumentation frequently have inherent non-linearities, may be affected by environmental conditions and can therefore cause calibration difficulties for the people who maintain them. Two neural network approaches are described in this paper for improving the accuracy of a non-linear, temperature sensitive level probe ised in Expermental Breeder Reactor II (EBR-II) that was difficult to calibrate.
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.
Parameters optimization of laser brazing in crimping butt using Taguchi and BPNN-GA
NASA Astrophysics Data System (ADS)
Rong, Youmin; Zhang, Zhen; Zhang, Guojun; Yue, Chen; Gu, Yafei; Huang, Yu; Wang, Chunming; Shao, Xinyu
2015-04-01
The laser brazing (LB) is widely used in the automotive industry due to the advantages of high speed, small heat affected zone, high quality of welding seam, and low heat input. Welding parameters play a significant role in determining the bead geometry and hence quality of the weld joint. This paper addresses the optimization of the seam shape in LB process with welding crimping butt of 0.8 mm thickness using back propagation neural network (BPNN) and genetic algorithm (GA). A 3-factor, 5-level welding experiment is conducted by Taguchi L25 orthogonal array through the statistical design method. Then, the input parameters are considered here including welding speed, wire speed rate, and gap with 5 levels. The output results are efficient connection length of left side and right side, top width (WT) and bottom width (WB) of the weld bead. The experiment results are embed into the BPNN network to establish relationship between the input and output variables. The predicted results of the BPNN are fed to GA algorithm that optimizes the process parameters subjected to the objectives. Then, the effects of welding speed (WS), wire feed rate (WF), and gap (GAP) on the sum values of bead geometry is discussed. Eventually, the confirmation experiments are carried out to demonstrate the optimal values were effective and reliable. On the whole, the proposed hybrid method, BPNN-GA, can be used to guide the actual work and improve the efficiency and stability of LB process.
Darwinian optimization of synthetic neural systems
Dress, W.B.
1987-01-01
This paper suggests a synthesis of computer science and artificial intelligence with the resurgent ideas of artificial neural systems and genetic algorithms cast in a classical Darwinian mold. Just as Darwin's original theory avoided the need for teleological arguments, the thrust of the approach set forth here for synthetic systems avoids the problem of programmer omniscience and the resulting brittle programs for precisely the same reasons. The price to be paid is one of many long computations on, perhaps, many parallel processors. Hardware development leading to parallel networks of RISC processors should meet the near-term needs of evolutionary parameter determination and allow the ensuring synthetic systems to function in real-time for certain tasks. In the longer term, special-purpose devices will be needed.
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
An optimization methodology for neural network weights and architectures.
Ludermir, Teresa B; Yamazaki, Akio; Zanchettin, Cleber
2006-11-01
This paper introduces a methodology for neural network global optimization. The aim is the simultaneous optimization of multilayer perceptron (MLP) network weights and architectures, in order to generate topologies with few connections and high classification performance for any data sets. The approach combines the advantages of simulated annealing, tabu search and the backpropagation training algorithm in order to generate an automatic process for producing networks with high classification performance and low complexity. Experimental results obtained with four classification problems and one prediction problem has shown to be better than those obtained by the most commonly used optimization techniques. PMID:17131660
Optimal groundwater remediation using artificial neural networks and the genetic algorithm
Rogers, L.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)
Jokar, Ali; Godarzi, Ali Abbasi; Saber, Mohammad; Shafii, Mohammad Behshad
2016-01-01
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.
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
2015-01-01
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
Neural optimal control of flexible spacecraft slew maneuver
NASA Astrophysics Data System (ADS)
Nayeri, M. Reza Dehghan; Alasty, Aria; Daneshjou, Kamran
2004-11-01
This paper deals with the problem of optimal large-angle single-axis maneuvers of a flexible spacecraft with simultaneous vibration suppression of elastic modes. A spacecraft model with a cylindrical hub and one flexible appendage and tip mass is considered. Gravity gradient torque is considered as a disturbance torque. Multilayer perceptron neural networks are used to design a Neural Optimal Controller (NOC) for this multivariable non-linear maneuver. For NOC training, an off-line training procedure based on backpropagation through time algorithm is developed to minimize the general quadratic cost function in forward and backward pass stages. The proposed controller is also applicable to simultaneous multi-axis reorientation of a flexible spacecraft. Simulation results are presented to show that very fast reference pitch angle trajectory tracking and vibration suppression are accomplished.
NASA Astrophysics Data System (ADS)
Zhang, Liqiang; Li, Luoxing; Wang, Shiuping; Zhu, Biwu
2012-04-01
In this article, the low-pressure die-cast (LPDC) process parameters of aluminum alloy thin-walled component with permanent mold are optimized using a combining artificial neural network and genetic algorithm (ANN/GA) method. In this method, an ANN model combining learning vector quantization (LVQ) and back-propagation (BP) algorithm is proposed to map the complex relationship between process conditions and quality indexes of LPDC. The genetic algorithm is employed to optimize the process parameters with the fitness function based on the trained ANN model. Then, by applying the optimized parameters, a thin-walled component with 300 mm in length, 100 mm in width, and 1.5 mm in thickness is successfully prepared and no obvious defects such as shrinkage, gas porosity, distortion, and crack were found in the component. The results indicate that the combining ANN/GA method is an effective tool for the process optimization of LPDC, and they also provide valuable reference on choosing the right process parameters for LPDC thin-walled aluminum alloy casting.
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
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
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.
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. PMID:25201976
NASA Astrophysics Data System (ADS)
Sahoo, G. B.
2007-12-01
In recent years, artificial neural networks (ANNs) appear to be viable alternative to models that use phenomenological hypotheses (i.e. knowledge based models) for cases (1) the available data are not detailed and sufficient for using a process based model and (2) the detailed complex physics of the system is partially understood. ANNs have been widely used in many fields such as chemical and environmental engineering, hydrology, and water resources applications for optimum prediction of system parameters and variables. However, in most cases, parameters and system variables were forecasted employing suboptimal ANNs. The geometry and modeling parameters of an artificial neural network (ANN) and the training dataset have significant effects on its predictive performance efficiency. The combination of ANN modeling parameter and geometry arranged in the modeling domain (i.e. lower and upper bounds of each modeling parameter and geometry) is large enough (i.e. greater than 100000) that it is difficult to examine all cases using trial and error approach for the selection of an optimum set. Thus, one could easily end up with finding a set of suboptimal values. This study presents the use of genetic algorithms (GAs) to search for the optimal geometry and values of modeling parameters of a multilayer feedforward backpropagation neural network (BPNN) and a radial basis function network (RBFN). The predictive performance efficiency of the GA and ANN combination is examined using two datasets derived from the same population for training. It is illustrated that (1) the GA optimized ANN outperforms to the ANN using a trial and error approach, and (2) ANN predictive performance and geometry depend on the number of samples and the characteristics of samples included in the training dataset.
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.
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
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
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. PMID:25647664
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.
Optimized approximation algorithm in neural networks without overfitting.
Liu, Yinyin; Starzyk, Janusz A; Zhu, Zhen
2008-06-01
In this paper, an optimized approximation algorithm (OAA) is proposed to address the overfitting problem in function approximation using neural networks (NNs). The optimized approximation algorithm avoids overfitting by means of a novel and effective stopping criterion based on the estimation of the signal-to-noise-ratio figure (SNRF). Using SNRF, which checks the goodness-of-fit in the approximation, overfitting can be automatically detected from the training error only without use of a separate validation set. The algorithm has been applied to problems of optimizing the number of hidden neurons in a multilayer perceptron (MLP) and optimizing the number of learning epochs in MLP's backpropagation training using both synthetic and benchmark data sets. The OAA algorithm can also be utilized in the optimization of other parameters of NNs. In addition, it can be applied to the problem of function approximation using any kind of basis functions, or to the problem of learning model selection when overfitting needs to be considered. PMID:18541499
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.
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.
Optimal groundwater remediation using artificial neural networks and the genetic algorithm
Rogers, L.L.
1992-01-01
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 trained network searches through realizations or patterns of pumping selected by the GA, predicting the outcome. This approach has advantages of parallel processing of the groundwater simulations and the ability to [open quotes]recycle[close quotes] 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. The ANN technology, inspired by neurobiological theories of massive interconnection and parallelism, has been applied to a variety of optimization problems. In the ANN groundwater management approach presented here, the behavior of complex groundwater scenarios with spatially-variable transport parameters and multiple contaminant plumes are simulated with 2-D flow and transport codes. An ANN is trained upon a set of examples developed from groundwater simulations. The input of the ANN characterizes the different realizations of pumping. The output characterizes the objectives and constraints of the optimization, such as whether regulatory goals have been met, value of cost functions or cleanup time, and mass of contaminant removal. The supervised learning algorithm of backpropagation is used to train the network. The conjugate gradient method and weight-elimination procedures are used to speed convergence and improve performance, respectively. Then a search is made through possible pumping realizations to find optimal realizations.
Statistical process control using optimized neural networks: a case study.
Addeh, Jalil; Ebrahimzadeh, Ata; Azarbad, Milad; Ranaee, Vahid
2014-09-01
The most common statistical process control (SPC) tools employed for monitoring process changes are control charts. A control chart demonstrates that the process has altered by generating an out-of-control signal. This study investigates the design of an accurate system for the control chart patterns (CCPs) recognition in two aspects. First, an efficient system is introduced that includes two main modules: feature extraction module and classifier module. In the feature extraction module, a proper set of shape features and statistical feature are proposed as the efficient characteristics of the patterns. In the classifier module, several neural networks, such as multilayer perceptron, probabilistic neural network and radial basis function are investigated. Based on an experimental study, the best classifier is chosen in order to recognize the CCPs. Second, a hybrid heuristic recognition system is introduced based on cuckoo optimization algorithm (COA) algorithm to improve the generalization performance of the classifier. The simulation results show that the proposed algorithm has high recognition accuracy. PMID:24210290
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. PMID:26221132
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. PMID:26221132
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.
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. PMID:25257715
Waveguide Optimization for Semipolar (In,Al,Ga)N Lasers
NASA Astrophysics Data System (ADS)
Rass, Jens; Ploch, Simon; Wernicke, Tim; Frentrup, Martin; Weyers, Markus; Kneissl, Michael
2013-08-01
In this work the optical waveguiding in semipolar InGaN-based laser diodes is analyzed. Different designs of the separate confinement heterostructure with AlGaN or GaN cladding layers and GaN or InGaN waveguide layers are studied. The influence of waveguide material, thickness and composition on the optical confinement factor Γ, the accumulated strain energy E and the refractive index contrast is calculated. Measurements of the threshold and the far field intensity distributions of lasers with differing waveguide design confirm the predictions from model calculations. The optimum waveguide for a 410 nm single quantum well laser is found to consist of a symmetric In0.04Ga0.96N waveguide of 2×85 nm thickness with GaN cladding layers.
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
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.
Discrete-time neural inverse optimal control for nonlinear systems via passivation.
Ornelas-Tellez, Fernando; Sanchez, Edgar N; Loukianov, Alexander G
2012-08-01
This paper presents a discrete-time inverse optimal neural controller, which is constituted by combination of two techniques: 1) inverse optimal control to avoid solving the Hamilton-Jacobi-Bellman equation associated with nonlinear system optimal control and 2) on-line neural identification, using a recurrent neural network trained with an extended Kalman filter, in order to build a model of the assumed unknown nonlinear system. The inverse optimal controller is based on passivity theory. The applicability of the proposed approach is illustrated via simulations for an unstable nonlinear system and a planar robot. PMID:24807528
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.
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. PMID:25986587
Zhang, Xing-Yi; Chen, Da-Wei; Jin, Jie; Lu, Wei
2009-10-01
Artificial neural network (ANN) is a multi-objective optimization method that needs mathematic and statistic knowledge which restricts its application in the pharmaceutical research area. An artificial neural network parameters optimization software (ANNPOS) programmed by the Visual Basic language was developed to overcome this shortcoming. In the design of a sustained release formulation, the suitable parameters of ANN were estimated by the ANNPOS. And then the Matlab 5.0 Neural Network Toolbox was used to determine the optimal formulation. It showed that the ANNPOS reduced the complexity and difficulty in the ANN's application. PMID:20055142
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.
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.
SEMICONDUCTOR MATERIALS: AlGaSb/GaSb quantum wells grown on an optimized AlSb nucleation layer
NASA Astrophysics Data System (ADS)
Hanchao, Gao; Cai, Wen; Wenxin, Wang; Zhongwei, Jiang; Haitao, Tian; Tao, He; Hui, Li; Hong, Chen
2010-05-01
Five-period AlGaSb/GaSb multiple quantum wells (MQW) are grown on a GaSb buffer. Through optimizing the AlSb nucleation layer, the low threading dislocation density of the MQW is found to be (2.50 ± 0.91) × 108 cm-2 in 1-μm GaSb buffer, as determined by plan-view transmission election microscopy (TEM) images. High resolution TEM clearly shows the presence of 90° misfit dislocations with an average spacing of 5.4 nm at the AlSb/GaAs interface, which effectively relieve most of the strain energy. In the temperature range from T = 26 K to 300 K, photoluminescence of the MQW is dominated by the ground state electron to ground state heavy hole (e1-hh1) transition, while a high energy shoulder clearly seen at T > 76 K can be attributed to the ground state electron to ground state light hole (e1-lh1) transition.
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.
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.
Optimal and robust design of brain-state-in-a-box neural associative memories.
Park, Yonmook
2010-03-01
This paper presents a new optimization approach to the design of associative memories via the brain-state-in-a-box (BSB) neural network. The optimization approach proposed in this paper provides the large and uniform domains of attraction of the prototype patterns, the large robustness margin for the weight matrix of the perturbed BSB neural network, the asymptotic stability of the prototype patterns, and the global stability of the BSB neural network. Based on some known qualitative properties of the BSB neural network and theoretical results presented in this paper, a synthesis method of the BSB-based associative memory is established. The synthesis method presented in this paper is given in the form of a linear matrix inequality-based optimization problem, which can be efficiently solved by a readily available software. Design examples are given to demonstrate the applicability of the proposed method and to compare with the existing synthesis methods. PMID:19914797
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.
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
Objective 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. Participants and methods 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. Results 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. Conclusions 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. PMID:21918622
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.
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.
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…
Optimal design of systems that evolve over time using neural networks
NASA Astrophysics Data System (ADS)
Nolan, Michael K.
2007-04-01
Design optimization is challenging when the number of variables becomes large. One method of addressing this problem is to use pattern recognition to decrease the solution space in which the optimizer searches. Human "common sense" is used by designers to narrow the scope of search to a confined area defined by patterns conforming to likely solution candidates. However, computer-based optimization generally does not apply similar heuristics. In this paper, a system is presented that recognizes patterns and adjusts its search for optimal solutions based on these patterns. A design problem was selected that requires the optimization algorithm to assess designs that evolve over time. A small sensor network design is evolved into a larger sensor network design. Optimal design solutions for the small network do not necessarily lead to optimal solutions for the larger network. Systems that are well-positioned to evolve have characteristics that distinguish themselves from systems that are not well-positioned to evolve. In this study, a neural network was able to recognize a pattern whereby flexible sensor networks evolved more successfully than less flexible networks. The optimizing algorithm used this pattern to select candidate systems that showed promise for evolution. A genetic algorithm assisted by a neural network achieved better performance than an unassisted genetic algorithm did. This thesis advocates the merit of neural network use in multi-objective system design optimization and to lay a basis for future study.
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.
Optimal Formation of Multirobot Systems Based on a Recurrent Neural Network.
Wang, Yunpeng; Cheng, Long; Hou, Zeng-Guang; Yu, Junzhi; Tan, Min
2016-02-01
The optimal formation problem of multirobot systems is solved by a recurrent neural network in this paper. The desired formation is described by the shape theory. This theory can generate a set of feasible formations that share the same relative relation among robots. An optimal formation means that finding one formation from the feasible formation set, which has the minimum distance to the initial formation of the multirobot system. Then, the formation problem is transformed into an optimization problem. In addition, the orientation, scale, and admissible range of the formation can also be considered as the constraints in the optimization problem. Furthermore, if all robots are identical, their positions in the system are exchangeable. Then, each robot does not necessarily move to one specific position in the formation. In this case, the optimal formation problem becomes a combinational optimization problem, whose optimal solution is very hard to obtain. Inspired by the penalty method, this combinational optimization problem can be approximately transformed into a convex optimization problem. Due to the involvement of the Euclidean norm in the distance, the objective function of these optimization problems are nonsmooth. To solve these nonsmooth optimization problems efficiently, a recurrent neural network approach is employed, owing to its parallel computation ability. Finally, some simulations and experiments are given to validate the effectiveness and efficiency of the proposed optimal formation approach. PMID:26316224
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
Design and optimization of GaAs photovoltaic converter for laser power beaming
NASA Astrophysics Data System (ADS)
Shan, Tiqiang; Qi, Xinglin
2015-07-01
GaAs photovoltaic (PV) converters are useful for the conversion of monochromatic light into electrical power in numerous military and industrial applications. The work of this paper is to design a monochromatic GaAs PV converter for coupling to laser beams in the wavelength of 790-840 nm and optimize its structure, layer thicknesses, doping levels of the emitter and base, and antireflection coating. Modeling calculations of the GaAs PV converter optimization are carried out using PC-1D. From the highest efficiency point of view, the best wavelength is 840 nm at which the optimized structure gives an efficiency of 61.8% theoretically. Experiment results under 808 nm laser power beaming show that high optical-to-electrical conversion efficiency of 53.23% at 5 W/cm2 is achieved using the optimized GaAs PV laser converter. Finally, accurate extraction of the key parameters, viz. the ideality factor, reverse saturation current, series resistance and shunt resistance is introduced. Variations of these parameters with illumination intensity are also investigated analytically based on the one diode model, which are necessary for the design of a high performance PV generation system.
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.
Lin, Mai; Ranganathan, David; Mori, Tetsuya; Hagooly, Aviv; Rossin, Raffaella; Welch, Michael J; Lapi, Suzanne E
2012-10-01
Interest in using (68)Ga is rapidly increasing for clinical PET applications due to its favorable imaging characteristics and increased accessibility. The focus of this study was to provide our long-term evaluations of the two TiO(2)-based (68)Ge/(68)Ga generators and develop an optimized automation strategy to synthesize [(68)Ga]DOTATOC by using HEPES as a buffer system. This data will be useful in standardizing the evaluation of (68)Ge/(68)Ga generators and automation strategies to comply with regulatory issues for clinical use. PMID:22897970
Benyamini, Miri; Zacksenhouse, Miriam
2015-01-01
Recent experiments with brain-machine-interfaces (BMIs) indicate that the extent of neural modulations increased abruptly upon starting to operate the interface, and especially after the monkey stopped moving its hand. In contrast, neural modulations that are correlated with the kinematics of the movement remained relatively unchanged. Here we demonstrate that similar changes are produced by simulated neurons that encode the relevant signals generated by an optimal feedback controller during simulated BMI experiments. The optimal feedback controller relies on state estimation that integrates both visual and proprioceptive feedback with prior estimations from an internal model. The processing required for optimal state estimation and control were conducted in the state-space, and neural recording was simulated by modeling two populations of neurons that encode either only the estimated state or also the control signal. Spike counts were generated as realizations of doubly stochastic Poisson processes with linear tuning curves. The model successfully reconstructs the main features of the kinematics and neural activity during regular reaching movements. Most importantly, the activity of the simulated neurons successfully reproduces the observed changes in neural modulations upon switching to brain control. Further theoretical analysis and simulations indicate that increasing the process noise during normal reaching movement results in similar changes in neural modulations. Thus, we conclude that the observed changes in neural modulations during BMI experiments can be attributed to increasing process noise associated with the imperfect BMI filter, and, more directly, to the resulting increase in the variance of the encoded signals associated with state estimation and the required control signal. PMID:26042002
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.
On the Current State of the Research in Neural Network and Optimization Methods
NASA Astrophysics Data System (ADS)
Onoda, Takashi; Someya, Hiroshi
This article surveys the history of the field of Neural Network research and presents a review of several techniques developed in the field. Attempts at statistical analysis of search dynamics of the optimization methods in Soft Computing and recent advances on implementation in parallel computers are briefly introduced.
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.
Zhang, Mei; Hu, Yueming; Wang, Tao; Zhu, Jinhui
2009-12-01
This paper addresses the predicting problem of peritoneal fluid absorption rate(PFAR). An innovative predicting model was developed, which employed the improved genetic algorithm embedded in neural network for predicting the important PFAR index in the peritoneal dialysis treatment process of renal failure. The significance of PFAR and the complexity of dialysis process were analyzed. The improved genetic algorithm was used for defining the initial weight and bias of neural network, and then the neural network was used for finding out the optimal predicting model of PFAR. This method utilizes the global search capability of genetic algorithm and the local search advantage of neural network completely. For the purpose of showing the validity of the model, the improved optimal predicting model is compared with the standard hybrid method of genetic algorithm and neural network. The simulation results show that the predicting accuracy of the improved optimal neural network is greatly improved and the learning process needs less time. PMID:20095466
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.
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
NASA Astrophysics Data System (ADS)
Liu, Chao; Cai, Yuefei; Jiang, Huaxing; Lau, Kei May
2016-04-01
For the development of a metal-interconnection-free integration scheme for monolithic integration of InGaN/GaN light-emitting diodes (LEDs) and AlGaN/GaN high-electron-mobility transistors (HEMTs), a common buffer to achieve high brightness, low leakage current, and high breakdown in the integrated HEMT-LED device is essential. Different buffer structures have been investigated, and their impacts upon both the LED and HEMT parts of the HEMT-LED device have been analyzed. Results indicated that a GaN/AlN buffer structure is the most ideal to serve as a common buffer platform, offering both the excellent crystalline quality and superior buffer resistivity required by the HEMT-LED device. Growth of the AlN layer was particularly crucial for engineering the dislocation density, surface morphology, as well as resistivity of the buffer layer. Using the optimized GaN/AlN buffer structure, the LED part of the HEMT-LED device was improved, showing greatly enhanced light output power and suppressed reverse leakage current, while the breakdown characteristics of the HEMT part were also improved.
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. PMID:25152929
Two neural network algorithms for designing optimal terminal controllers with open final time
NASA Technical Reports Server (NTRS)
Plumer, Edward S.
1992-01-01
Multilayer neural networks, trained by the backpropagation through time algorithm (BPTT), have been used successfully as state-feedback controllers for nonlinear terminal control problems. Current BPTT techniques, however, are not able to deal systematically with open final-time situations such as minimum-time problems. Two approaches which extend BPTT to open final-time problems are presented. In the first, a neural network learns a mapping from initial-state to time-to-go. In the second, the optimal number of steps for each trial run is found using a line-search. Both methods are derived using Lagrange multiplier techniques. This theoretical framework is used to demonstrate that the derived algorithms are direct extensions of forward/backward sweep methods used in N-stage optimal control. The two algorithms are tested on a Zermelo problem and the resulting trajectories compare favorably to optimal control results.
A 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
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. PMID:25190869
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 paper, we present the highest performing free-paced neural prosthesis under any recording modality with sustainable communication rates of up to 3.5 bits/s. 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
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.
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.
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
Application of GA-SVM method with parameter optimization for landslide development prediction
NASA Astrophysics Data System (ADS)
Li, X. Z.; Kong, J. M.
2014-03-01
Prediction of the landslide development process is always a hot issue in landslide research. So far, many methods for landslide displacement series prediction have been proposed. The support vector machine (SVM) has been proved to be a novel algorithm with good performance. However, the performance strongly depends on the right selection of the parameters (C and γ) of the SVM model. In this study, we present an application of genetic algorithm and support vector machine (GA-SVM) method with parameter optimization in landslide displacement rate prediction. We selected a typical large-scale landslide in a hydro-electrical engineering area of southwest China as a case. On the basis of analyzing the basic characteristics and monitoring data of the landslide, a single-factor GA-SVM model and a multi-factor GA-SVM model of the landslide were built. Moreover, the models were compared with single-factor and multi-factor SVM models of the landslide. The results show that the four models have high prediction accuracies, but the accuracies of GA-SVM models are slightly higher than those of SVM models, and the accuracies of multi-factor models are slightly higher than those of single-factor models for the landslide prediction. The accuracy of the multi-factor GA-SVM models is the highest, with the smallest root mean square error (RMSE) of 0.0009 and the highest relation index (RI) of 0.9992.
Application of GA-SVM method with parameter optimization for landslide development prediction
NASA Astrophysics Data System (ADS)
Li, X. Z.; Kong, J. M.
2013-10-01
Prediction of landslide development process is always a hot issue in landslide research. So far, many methods for landslide displacement series prediction have been proposed. Support vector machine (SVM) has been proved to be a novel algorithm with good performance. However, the performance strongly depends on the right selection of the parameters (C and γ) of SVM model. In this study, we presented an application of GA-SVM method with parameter optimization in landslide displacement rate prediction. We selected a typical large-scale landslide in some hydro - electrical engineering area of Southwest China as a case. On the basis of analyzing the basic characteristics and monitoring data of the landslide, a single-factor GA-SVM model and a multi-factor GA-SVM model of the landslide were built. Moreover, the models were compared with single-factor and multi-factor SVM models of the landslide. The results show that, the four models have high prediction accuracies, but the accuracies of GA-SVM models are slightly higher than those of SVM models and the accuracies of multi-factor models are slightly higher than those of single-factor models for the landslide prediction. The accuracy of the multi-factor GA-SVM models is the highest, with the smallest RSME of 0.0009 and the biggest RI of 0.9992.
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.
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.
Optimizing protocols for imaging neural cells and tissues using functionalized quantum dots
NASA Astrophysics Data System (ADS)
Pathak, Smita; Silva, Gabriel A.
2008-02-01
Chemically functionalized semiconductor quantum dot protocols were optimized for the specific labeling and imaging of neural cells, both neurons and macroglial cells. Beta-tubulin III was used to image primary cortical neurons and PC12 cells while glial fibrillary acidic protein (GFAP) was used to image primary spinal cord and cortical astrocytes and the rMC-1 retinal glial Muller cell line. Both proteins are the main components of intermediate filaments and are specific to the two classes of neural cells. We also specifically labeled and imaged at high resolutions using anti-GFAP conjugated quantum dots glial scars in situ in intact neural sensory retina in a rodent model of macular degeneration.
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.
Optimally efficient neural systems for processing spoken language.
Zhuang, Jie; Tyler, Lorraine K; Randall, Billi; Stamatakis, Emmanuel A; Marslen-Wilson, William D
2014-04-01
Cognitive models claim that spoken words are recognized by an optimally efficient sequential analysis process. Evidence for this is the finding that nonwords are recognized as soon as they deviate from all real words (Marslen-Wilson 1984), reflecting continuous evaluation of speech inputs against lexical representations. Here, we investigate the brain mechanisms supporting this core aspect of word recognition and examine the processes of competition and selection among multiple word candidates. Based on new behavioral support for optimal efficiency in lexical access from speech, a functional magnetic resonance imaging study showed that words with later nonword points generated increased activation in the left superior and middle temporal gyrus (Brodmann area [BA] 21/22), implicating these regions in dynamic sound-meaning mapping. We investigated competition and selection by manipulating the number of initially activated word candidates (competition) and their later drop-out rate (selection). Increased lexical competition enhanced activity in bilateral ventral inferior frontal gyrus (BA 47/45), while increased lexical selection demands activated bilateral dorsal inferior frontal gyrus (BA 44/45). These findings indicate functional differentiation of the fronto-temporal systems for processing spoken language, with left middle temporal gyrus (MTG) and superior temporal gyrus (STG) involved in mapping sounds to meaning, bilateral ventral inferior frontal gyrus (IFG) engaged in less constrained early competition processing, and bilateral dorsal IFG engaged in later, more fine-grained selection processes. PMID:23250955
Vrabie, Draguna; Lewis, Frank
2009-04-01
In this paper we present in a continuous-time framework an online approach to direct adaptive optimal control with infinite horizon cost for nonlinear systems. The algorithm converges online to the optimal control solution without knowledge of the internal system dynamics. Closed-loop dynamic stability is guaranteed throughout. The algorithm is based on a reinforcement learning scheme, namely Policy Iterations, and makes use of neural networks, in an Actor/Critic structure, to parametrically represent the control policy and the performance of the control system. The two neural networks are trained to express the optimal controller and optimal cost function which describes the infinite horizon control performance. Convergence of the algorithm is proven under the realistic assumption that the two neural networks do not provide perfect representations for the nonlinear control and cost functions. The result is a hybrid control structure which involves a continuous-time controller and a supervisory adaptation structure which operates based on data sampled from the plant and from the continuous-time performance dynamics. Such control structure is unlike any standard form of controllers previously seen in the literature. Simulation results, obtained considering two second-order nonlinear systems, are provided. PMID:19362449
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
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 Astrophysics Data System (ADS)
Pan, Zhongliang; Li, Wei; Shao, Qingyi; Chen, Ling
2011-12-01
In the design procedure of system on chip (SoC), it is needed to make use of hardware-software co-design technique owing to the great complexity of SoC. One of main steps in hardware-software co-design is how to carry out the partitioning of a system into hardware and software components. The efficient approaches for hardware-software partitioning can achieve good system performance, which is superior to the techniques that use software only or use hardware only. In this paper, a method based on neural networks is presented for the hardware-software partitioning of system on chip. The discrete Hopfield neural networks corresponding to the problem of hardware-software partitioning is built, the states of neural neurons are able to represent whether the required components or functionalities are to be implemented in hardware or software. An algorithm based on the principle of simulated annealing is designed, which can be used to compute the minimal energy states of neural networks, therefore the optimal partitioning schemes are obtained. The experimental results show that the hardware-software partitioning method proposed in this paper can obtain the near optimal partitioning for a lot of example circuits.
Neural network-based combustion optimization reduces NOx emissions while improving performance
Booth, R.C.; Roland, W.B.
1998-07-01
This paper presents the benefits of applying an on-line, real-time neural network to several bituminous coal fired utility boilers. The system helps reduce NOx emissions up to 60%, meeting compliance while it improves heat rate up to 2% overall (5% at low load) and reduces LOI as much as 30% through combustion optimization alone. The system can avoid or postpone large capital expenditures for low NOx burners, overfire air boiler modifications, SCRs, and SNCRs. The neural network-based system has been applied on 11 electric utility boilers that represent a wide range of furnace and burner types including units with tangential-, cell-, single wall-, and opposed wall-burner arrangements that have ranged in capacity from 146 to 800 MW in an advisory mode. Several sites have employed the neural network-based system for closed-loop supervisory combustion control. Boiler combustion profiles change continuously due to coal quality, boiler loading, changes in slag/soot deposits, ambient conditions, and the condition of plant equipment. Through on-line retraining, the neural network-based system optimizes the boiler operation by accommodating equipment performance changes due to wear and maintenance activities, adjusting to fluctuations in fuel quality, and improving operating flexibility. The system dynamically adjusts combustion setpoints and bias settings in closed-loop supervisory control to reduce NO{sub x} emissions and improve heat rate simultaneously.
NASA Astrophysics Data System (ADS)
Tangpatiphan, Kritsana; Yokoyama, Akihiko
This paper presents an adaptive evolutionary programming incorporating neural network for solving transient stability constrained optimal power flow (TSCOPF). The proposed AEP method is an evolutionary programming (EP)-based algorithm, which adjusts its population size automatically during an optimization process. The artificial neural network, which classifies the AEP individual based on its stability degrees, is embedded into the search template to reduce the computational load caused by transient stability constraints. The fuel cost minimization is selected as the objective function of TSCOPF. The proposed method is tested on the IEEE 30-bus system with two types of the fuel cost functions, i.e. the conventional quadratic function and the quadratic function superimposed by sine component to model the cost curves without and with valve-point loading effect respectively. The numerical examples show that AEP is more effective than conventional EP in terms of computational speed, and when the neural network is incorporated into AEP, it can significantly reduce the computational time of TSCOPF. A study of the architecture of the neural network is also conducted and discussed. In addition, the effectiveness of the proposed method for solving TSCOPF with the consideration of multiple contingencies is manifested.
Neural network-based combustion optimization reduces NOx emissions while improving performance
Booth, R.C.; Roland, W.B. Jr.
1998-12-31
The NeuSIGHT neural network based system has been applied to units with tangential-, cell-, single wall-, and opposed wall-burner arrangements that have ranged in capacity from 146 to 800 MW in an advisory mode. Several sites have employed the neural network-based system for closed-loop supervisory combustion control. Boiler combustion profiles change continuously due to coal quality, boiler loading, changes in slag/soot deposits, ambient conditions, and the condition of plant equipment. Through on-line retraining, the neural network-based system optimizes the boiler operation by accommodating equipment performance changes due to wear and maintenance activities, adjusting to fluctuations in fuel quality, and improving operating flexibility. The system dynamically adjusts combustion setpoints and bias settings in closed-loop supervisory control to reduce NO{sub x} emissions and improve heat rate simultaneously. This paper presents the benefits of applying an on-line, real-time neural network to several commercially operating bituminous coal fired utility boilers. The system helps reduce NO{sub x} emissions up to 60%, meeting compliance while it improves heat rate up to 2% overall (5% at low load) and reduces LOI as much as 30% through combustion optimization alone. The system can avoid or postpone large capital expenditures for low NO{sub x} burners, overfire air boiler modifications, SCRs, and SNCRs.
García-Pedrajas, Nicolás; Ortiz-Boyer, Domingo; Hervás-Martínez, César
2006-05-01
In this work we present a new approach to crossover operator in the genetic evolution of neural networks. The most widely used evolutionary computation paradigm for neural network evolution is evolutionary programming. This paradigm is usually preferred due to the problems caused by the application of crossover to neural network evolution. However, crossover is the most innovative operator within the field of evolutionary computation. One of the most notorious problems with the application of crossover to neural networks is known as the permutation problem. This problem occurs due to the fact that the same network can be represented in a genetic coding by many different codifications. Our approach modifies the standard crossover operator taking into account the special features of the individuals to be mated. We present a new model for mating individuals that considers the structure of the hidden layer and redefines the crossover operator. As each hidden node represents a non-linear projection of the input variables, we approach the crossover as a problem on combinatorial optimization. We can formulate the problem as the extraction of a subset of near-optimal projections to create the hidden layer of the new network. This new approach is compared to a classical crossover in 25 real-world problems with an excellent performance. Moreover, the networks obtained are much smaller than those obtained with classical crossover operator. PMID:16343847
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
Optimal structural design of the midship of a VLCC based on the strategy integrating SVM and GA
NASA Astrophysics Data System (ADS)
Sun, Li; Wang, Deyu
2012-03-01
In this paper a hybrid process of modeling and optimization, which integrates a support vector machine (SVM) and genetic algorithm (GA), was introduced to reduce the high time cost in structural optimization of ships. SVM, which is rooted in statistical learning theory and an approximate implementation of the method of structural risk minimization, can provide a good generalization performance in metamodeling the input-output relationship of real problems and consequently cuts down on high time cost in the analysis of real problems, such as FEM analysis. The GA, as a powerful optimization technique, possesses remarkable advantages for the problems that can hardly be optimized with common gradient-based optimization methods, which makes it suitable for optimizing models built by SVM. Based on the SVM-GA strategy, optimization of structural scantlings in the midship of a very large crude carrier (VLCC) ship was carried out according to the direct strength assessment method in common structural rules (CSR), which eventually demonstrates the high efficiency of SVM-GA in optimizing the ship structural scantlings under heavy computational complexity. The time cost of this optimization with SVM-GA has been sharply reduced, many more loops have been processed within a small amount of time and the design has been improved remarkably.
Classification of land cover using optimized neural nets on SPOT data
Dreyer, P. )
1993-05-01
An optimized neural net was developed for land-cover classification in a multispectral SPOT satellite image covering 10 km x 10 km region which contains a mixture of densely built-up areas, suburbs, rural land, and waterbodies. In the technique, segments in the image are described by textural features calculated from gray-level difference statistics. The size of the input layer (i.e., the input variables to be used), as well as the size of the hidden layer in the neural net are determined using the optimization algorithm proposed by Mozer and Smolensky (1989). The textural features are calculated in segments generated by region growing in an image which has been processed iteratively with an edge enhancing adaptive filter. 15 refs.
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
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.
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.
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.
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.
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.
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. PMID:25310846
InGaN/GaN multilayer quantum dots yellow-green light-emitting diode with optimized GaN barriers.
Lv, Wenbin; Wang, Lai; Wang, Jiaxing; Hao, Zhibiao; Luo, Yi
2012-01-01
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 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.
Simulation and optimization of current matching double-junction InGaN/Si solar cells
NASA Astrophysics Data System (ADS)
Nacer, S.; Aissat, A.
2016-02-01
This paper deals with theoretical investigation of the performance of current-matched In x GaN/Si double-junction solar cells. Calculations were performed under 1-sun AM1.5 using the one diode ideal model. Impact of minor carrier lifetime and surface recombination velocity in the top sub-cell on the cell performances is analyzed. Optimum composition of the top sub-cell has been identified ( x = 51.8 % and E g = 1.68 eV). The simulation results predict, for the optimized InGaN/Si double-junction solar cell, a short-circuit current J sc = 20 mA/cm2, an open-circuit voltage V oc = 1.97 V, and a conversion efficiency η = 38.3%.
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.
Optimization of ion-exchange protein separations using a vector quantizing neural network.
Klein, E J; Rivera, S L; Porter, J E
2000-01-01
In this work, a previously proposed methodology for the optimization of analytical scale protein separations using ion-exchange chromatography is subjected to two challenging case studies. The optimization methodology uses a Doehlert shell design for design of experiments and a novel criteria function to rank chromatograms in order of desirability. This chromatographic optimization function (COF) accounts for the separation between neighboring peaks, the total number of peaks eluted, and total analysis time. The COF is penalized when undesirable peak geometries (i.e., skewed and/or shouldered peaks) are present as determined by a vector quantizing neural network. Results of the COF analysis are fit to a quadratic response model, which is optimized with respect to the optimization variables using an advanced Nelder and Mead simplex algorithm. The optimization methodology is tested on two case study sample mixtures, the first of which is composed of equal parts of lysozyme, conalbumin, bovine serum albumin, and transferrin, and the second of which contains equal parts of conalbumin, bovine serum albumin, tranferrin, beta-lactoglobulin, insulin, and alpha -chymotrypsinogen A. Mobile-phase pH and gradient length are optimized to achieve baseline resolution of all solutes for both case studies in acceptably short analysis times, thus demonstrating the usefulness of the empirical optimization methodology. PMID:10835256
LIU, RUIXIN; ZHANG, XIAODONG; ZHANG, LU; GAO, XIAOJIE; LI, HUILING; SHI, JUNHAN; LI, XUELIN
2014-01-01
The aim of this study was to predict the bitterness intensity of a drug using an electronic tongue (e-tongue). The model drug of berberine hydrochloride was used to establish a bitterness prediction model (BPM), based on the taste evaluation of bitterness intensity by a taste panel, the data provided by the e-tongue and a genetic algorithm-back-propagation neural network (GA-BP) modeling method. The modeling characteristics of the GA-BP were compared with those of multiple linear regression, partial least square regression and BP methods. The determination coefficient of the BPM was 0.99965±0.00004, the root mean square error of cross-validation was 0.1398±0.0488 and the correlation coefficient of the cross-validation between the true and predicted values was 0.9959±0.0027. The model is superior to the other three models based on these indicators. In conclusion, the model established in this study has a high fitting degree and may be used for the bitterness prediction modeling of berberine hydrochloride of different concentrations. The model also provides a reference for the generation of BPMs of other drugs. Additionally, the algorithm of the study is able to conduct a rapid and accurate quantitative analysis of the data provided by the e-tongue. PMID:24926369
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.
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
Optimizing Semantic Pointer Representations for Symbol-Like Processing in Spiking Neural Networks
Gosmann, Jan; Eliasmith, Chris
2016-01-01
The Semantic Pointer Architecture (SPA) is a proposal of specifying the computations and architectural elements needed to account for cognitive functions. By means of the Neural Engineering Framework (NEF) this proposal can be realized in a spiking neural network. However, in any such network each SPA transformation will accumulate noise. By increasing the accuracy of common SPA operations, the overall network performance can be increased considerably. As well, the representations in such networks present a trade-off between being able to represent all possible values and being only able to represent the most likely values, but with high accuracy. We derive a heuristic to find the near-optimal point in this trade-off. This allows us to improve the accuracy of common SPA operations by up to 25 times. Ultimately, it allows for a reduction of neuron number and a more efficient use of both traditional and neuromorphic hardware, which we demonstrate here. PMID:26900931
Optimizing Semantic Pointer Representations for Symbol-Like Processing in Spiking Neural Networks.
Gosmann, Jan; Eliasmith, Chris
2016-01-01
The Semantic Pointer Architecture (SPA) is a proposal of specifying the computations and architectural elements needed to account for cognitive functions. By means of the Neural Engineering Framework (NEF) this proposal can be realized in a spiking neural network. However, in any such network each SPA transformation will accumulate noise. By increasing the accuracy of common SPA operations, the overall network performance can be increased considerably. As well, the representations in such networks present a trade-off between being able to represent all possible values and being only able to represent the most likely values, but with high accuracy. We derive a heuristic to find the near-optimal point in this trade-off. This allows us to improve the accuracy of common SPA operations by up to 25 times. Ultimately, it allows for a reduction of neuron number and a more efficient use of both traditional and neuromorphic hardware, which we demonstrate here. PMID:26900931
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.
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. PMID:11152205
NASA Astrophysics Data System (ADS)
Liu, Derong; Huang, Yuzhu; Wang, Ding; Wei, Qinglai
2013-09-01
In this paper, an observer-based optimal control scheme is developed for unknown nonlinear systems using adaptive dynamic programming (ADP) algorithm. First, a neural-network (NN) observer is designed to estimate system states. Then, based on the observed states, a neuro-controller is constructed via ADP method to obtain the optimal control. In this design, two NN structures are used: a three-layer NN is used to construct the observer which can be applied to systems with higher degrees of nonlinearity and without a priori knowledge of system dynamics, and a critic NN is employed to approximate the value function. The optimal control law is computed using the critic NN and the observer NN. Uniform ultimate boundedness of the closed-loop system is guaranteed. The actor, critic, and observer structures are all implemented in real-time, continuously and simultaneously. Finally, simulation results are presented to demonstrate the effectiveness of the proposed control scheme.
Optimization of ion-atomic beam source for deposition of GaN ultrathin films
Mach, Jindřich Kolíbal, Miroslav; Zlámal, Jakub; Voborny, Stanislav; Bartošík, Miroslav; Šikola, Tomáš; Šamořil, Tomáš
2014-08-15
We describe the optimization and application of an ion-atomic beam source for ion-beam-assisted deposition of ultrathin films in ultrahigh vacuum. The device combines an effusion cell and electron-impact ion beam source to produce ultra-low energy (20–200 eV) ion beams and thermal atomic beams simultaneously. The source was equipped with a focusing system of electrostatic electrodes increasing the maximum nitrogen ion current density in the beam of a diameter of ≈15 mm by one order of magnitude (j ≈ 1000 nA/cm{sup 2}). Hence, a successful growth of GaN ultrathin films on Si(111) 7 × 7 substrate surfaces at reasonable times and temperatures significantly lower (RT, 300 °C) than in conventional metalorganic chemical vapor deposition technologies (≈1000 °C) was achieved. The chemical composition of these films was characterized in situ by X-ray Photoelectron Spectroscopy and morphology ex situ using Scanning Electron Microscopy. It has been shown that the morphology of GaN layers strongly depends on the relative Ga-N bond concentration in the layers.
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.
NASA Astrophysics Data System (ADS)
Radosavljević, S.; Radovanović, J.; Milanović, V.; Tomić, S.
2014-07-01
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.
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, 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 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.
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
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
Kavitha, Ganesan; Ramakrishnan, Swaminathan
2010-01-01
Optic disc and retinal vasculature are important anatomical structures in the retina of the eye and any changes observed in these structures provide vital information on severity of various diseases. Digital retinal images are shown to provide a meaningful way of documenting and assessing some of the key elements inside the eye including the optic nerve and the tiny retinal blood vessels. In this work, an attempt has been made to detect and differentiate abnormalities of the retina using Digital image processing together with Optimization based segmentation and Artificial Neural Network methods. The retinal fundus images were recorded using standard protocols. Ant Colony Optimization is employed to extract the most significant objects namely the optic disc and blood vessel. The features related to these objects are obtained and corresponding indices are also derived. Further, these features are subjected to classification using Radial Basis Function Neural Networks and compared with conventional training algorithms. Results show that the Ant Colony Optimization is efficient in extracting useful information from retinal images. The features derived are effective for classification of normal and abnormal images using Radial basis function networks compared to other methods. As Optic disc and blood vessels are significant markers of abnormality in retinal images, the method proposed appears to be useful for mass screening. In this paper, the objectives of the study, methodology and significant observations are presented. PMID:20467104
Optimization of sputter deposition parameters for magnetostrictive Fe62Co19Ga19/Si(100) films
NASA Astrophysics Data System (ADS)
Jen, S. U.; Tsai, T. L.
2012-04-01
A good magnetostrictive material should have large saturation magnetostriction (λS) and low saturation (or anisotropy) field (HS), such that its magnetostriction susceptibility (SH) can be as large as possible. In this study, we have made Fe62Co19Ga19/Si(100) nano-crystalline films by using the dc magnetron sputtering technique under various deposition conditions: Ar working gas pressure (pAr) was varied from 1 to 15 mTorr; sputtering power (Pw) was from 10 to 120 W; deposition temperature (TS) was from room temperature (RT) to 300 °C, The film thickness (tf) was fixed at 175 nm. Each magnetic domain looked like a long leaf, with a long-axis of about 12-15 μm and a short-axis of about 1.5 μm. The optimal magnetic and electrical properties were found from the Fe62Co19Ga19 film made with the sputter deposition parameters of pAr = 5 mTorr, Pw = 80 W, and TS = RT. Those optimal properties include λS = 80 ppm, HS = 19.8 Oe, SH = 6.1 ppm/Oe, and electrical resistivity ρ = 57.0 μΩ cm. Note that SH for the conventional magnetostrictive Terfenol-D film is, in general, equal to 1.5 ppm/Oe only.
NASA Astrophysics Data System (ADS)
Gurcan, Metin N.; Chan, Heang-Ping; Sahiner, Berkman; Hadjiiski, Lubomir M.; Petrick, Nicholas; Helvie, Mark A.
2002-05-01
We evaluated the effectiveness of an optimal convolution neural network (CNN) architecture selected by simulated annealing for improving the performance of a computer-aided diagnosis (CAD) system designed for the detection of microcalcification clusters on digitized mammograms. The performances of the CAD programs with manually and optimally selected CNNs were compared using an independent test set. This set included 472 mammograms and contained 253 biopsy-proven malignant clusters. Free-response receiver operating characteristic (FROC) analysis was used for evaluation of the detection accuracy. At a false positive (FP) rate of 0.7 per image, the film-based sensitivity was 84.6% with the optimized CNN, in comparison with 77.2% with the manually selected CNN. If clusters having images in both craniocaudal and mediolateral oblique views were analyzed together and a cluster was considered to be detected when it was detected in one or both views, at 0.7 FPs/image, the sensitivity was 93.3% with the optimized CNN and 87.0% with the manually selected CNN. This study indicates that classification of true positive and FP signals is an important step of the CAD program and that the detection accuracy of the program can be considerably improved by optimizing this step with an automated optimization algorithm.
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.
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.
a Hybrid Approach of Neural Network with Particle Swarm Optimization for Tobacco Pests Prediction
NASA Astrophysics Data System (ADS)
Lv, Jiake; Wang, Xuan; Xie, Deti; Wei, Chaofu
Forecasting pests emergence levels plays a significant role in regional crop planting and management. The accuracy, which is derived from the accuracy of the forecasting approach used, will determine the economics of the operation of the pests prediction. Conventional methods including time series, regression analysis or ARMA model entail exogenous input together with a number of assumptions. The use of neural networks has been shown to be a cost-effective technique. But their training, usually with back-propagation algorithm or other gradient algorithms, is featured with some drawbacks such as very slow convergence and easy entrapment in a local minimum. This paper presents a hybrid approach of neural network with particle swarm optimization for developing the accuracy of predictions. The approach is applied to forecast Alternaria alternate Keissl emergence level of the WuLong Country, one of the most important tobacco planting areas in Chongqing. Traditional ARMA model and BP neural network are investigated as comparison basis. The experimental results show that the proposed approach can achieve better prediction performance.
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
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
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.
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.
NASA Astrophysics Data System (ADS)
Sitnikov, A. A.; Makarova, N. A.; Kamyshov, U. N.
2016-04-01
The authors have developed the procedure of optimization of the equipment configuration with the help of neural net based on the results of finite element analysis. The dismembrator's characteristics for feeding slop production has been optimized. The results of the virtual experiment are displayed in diagrams of pressure and temperature of the liquid inside the operating devices. The equipment of the optimized configuration has demonstrated a number of advantages compared to the prototype.
Supervised feature ranking using a genetic algorithm optimized artificial neural network.
Lin, Thy-Hou; Chiu, Shih-Hau; Tsai, Keng-Chang
2006-01-01
A genetic algorithm optimized artificial neural network GNW has been designed to rank features for two diversified multivariate data sets. The dimensions of these data sets are 85x24 and 62x25 for 24 or 25 molecular descriptors being computed for 85 matrix metalloproteinase-1 inhibitors or 62 hepatitis C virus NS3 protease inhibitors, respectively. Each molecular descriptor computed is treated as a feature and input into an input layer node of the artificial neural network. To optimize the artificial neural network by the genetic algorithm, each interconnected weight between input and hidden or between hidden and output layer nodes is binary encoded as a 16 bits string in a chromosome, and the chromosome is evolved by crossover and mutation operations. Each input layer node and its associated weights of the trained GNW are systematically omitted once (the self-depleted weights), and the corresponding weight adjustments due to the omission are computed to keep the overall network behavior unchanged. The primary feature ranking index defined as the sum of self-depleted weights and the corresponding weight adjustments computed is found capable of separating good from bad features for some artificial data sets of known feature rankings tested. The final feature indexes used to rank the data sets are computed as a sum of the weighted frequency of each feature being ranked in a particular rank for each data set being partitioned into numerous clusters. The two data sets are also clustered by a standard K-means method and trained by a support vector machine (SVM) for feature ranking using the computed F-scores as feature ranking index. It is found that GNW outperforms the SVM method on three artificial as well as the matrix metalloproteinase-1 inhibitor data sets studied. A clear-cut separation of good from bad features is offered by the GNW but not by the SVM method for a feature pool of known feature ranking. PMID:16859292
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. PMID:27155267
NASA Astrophysics Data System (ADS)
Sathiya, P.; Panneerselvam, K.; Soundararajan, R.
2012-09-01
Laser welding input parameters play a very significant role in determining the quality of a weld joint. The joint quality can be defined in terms of properties such as weld bead geometry, mechanical properties and distortion. Therefore, mechanical properties should be controlled to obtain good welded joints. In this study, the weld bead geometry such as depth of penetration (DP), bead width (BW) and tensile strength (TS) of the laser welded butt joints made of AISI 904L super austenitic stainless steel were investigated. Full factorial design was used to carry out the experimental design. Artificial Neural networks (ANN) program was developed in MatLab software to establish the relationships between the laser welding input parameters like beam power, travel speed and focal position and the three responses DP, BW and TS in three different shielding gases (Argon, Helium and Nitrogen). The established models were used for optimizing the process parameters using Genetic Algorithm (GA). Optimum solutions for the three different gases and their respective responses were obtained. Confirmation experiment has also been conducted to validate the optimized parameters obtained from GA.
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. PMID:24982962
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. PMID:22738782
NASA Astrophysics Data System (ADS)
Papila, Nilay Uzgoren
Turbine performance directly affects engine specific impulse, thrust-to-weight ratio, and cost in a rocket propulsion system. This dissertation focuses on methodology and application of employing optimization techniques, with the neural network (NN) and polynomial-based response surface method (RSM), for supersonic turbine optimization. The research is relevant to NASA's reusable launching vehicle initiatives. It is demonstrated that accuracy of the response surface (RS) approximations can be improved with combined utilization of the NN and polynomial techniques, and higher emphases on data in regions of interests. The design of experiment methodology is critical while performing optimization in efficient and effective manners. In physical applications, both preliminary design and detailed shape design optimization are investigated. For preliminary design level, single-, two-, and three-stage turbines are considered with the number of design variables increasing from six to 11 and then to 15, in accordance with the number of stages. A major goal of the preliminary optimization effort is to balance the desire of maximizing aerodynamic performance and minimizing weight. To ascertain required predictive capability of the RSM, a two-level domain refinement approach (windowing) has been adopted. The accuracy of the predicted optimal design points based on this strategy is shown to be satisfactory. The results indicate that the two-stage turbine is the optimum configuration with the higher efficiency corresponding to smaller weights. It is demonstrated that the criteria for selecting the database exhibit significant impact on the efficiency and effectiveness of the construction of the response surface. Based on the optimized preliminary design outcome, shape optimization is performed for vanes and blades of a two-stage supersonic turbine, involving O(10) design variables. It is demonstrated that a major merit of the RS-based optimization approach is that it enables one
NASA Astrophysics Data System (ADS)
Lekhal, Kaddour; Hussain, Sakhawat; De Mierry, Philippe; Vennéguès, Philippe; Nemoz, Maud; Chauveau, Jean-Michel; Damilano, Benjamin
2016-01-01
Yellow-emitting InxGa1-xN/GaN multiple quantum wells (MQWs) with different pairs of In composition and QW thickness have been grown by metal-organic chemical vapor deposition on sapphire substrates. We show that a trade-off between the MQW crystalline quality and the quantum confined Stark effect has to be found to maximize the room temperature photoluminescence efficiency. With our growth conditions, an optimum design of the MQW is obtained for x=0.21 and a QW thickness of 3.6 nm.
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. PMID:25720004
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.
Fjodorova, Natalja; Novič, Marjana
2015-09-01
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. PMID:26388367
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.
Modares, Hamidreza; Lewis, Frank L; Naghibi-Sistani, Mohammad-Bagher
2013-10-01
This paper presents an online policy iteration (PI) algorithm to learn the continuous-time optimal control solution for unknown constrained-input systems. The proposed PI algorithm is implemented on an actor-critic structure where two neural networks (NNs) are tuned online and simultaneously to generate the optimal bounded control policy. The requirement of complete knowledge of the system dynamics is obviated by employing a novel NN identifier in conjunction with the actor and critic NNs. It is shown how the identifier weights estimation error affects the convergence of the critic NN. A novel learning rule is developed to guarantee that the identifier weights converge to small neighborhoods of their ideal values exponentially fast. To provide an easy-to-check persistence of excitation condition, the experience replay technique is used. That is, recorded past experiences are used simultaneously with current data for the adaptation of the identifier weights. Stability of the whole system consisting of the actor, critic, system state, and system identifier is guaranteed while all three networks undergo adaptation. Convergence to a near-optimal control law is also shown. The effectiveness of the proposed method is illustrated with a simulation example. PMID:24808590
Total Wiring Length Minimization of C. elegans Neural Network: A Constrained Optimization Approach
Gushchin, Andrey; Tang, Ao
2015-01-01
Using the most recent data on the connectivity of the C. elegans neural network, we find optimal two-dimensional positions of interneurons that minimize the total wiring length provided that the positions of motor and sensory neurons are fixed. The rationale behind fixing motor and sensory neurons is the following: while positions of motor and sensory neurons can be influenced by the locations of muscles and sensory organs they are attached to, the main function of interneurons is to connect other neurons, and their placement could try to minimize the wiring length. Solutions for l1, l2 and squared l2–norm were obtained. For the Euclidean norm l2, the relative and absolute difference between the real and optimal total wiring lengths is minimal among these functions of distance. Additional network constraints were discussed such as assignment of different weights to electrical or chemical connections, fixation of “tail” interneurons, minimal interneural distance limitation, and others. These constraints were compared by their influence on the optimal positions of interneurons. PMID:26659722
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. PMID:24808521
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.
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. PMID:20403598
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.
NASA Astrophysics Data System (ADS)
Wagner, J.; Schmitz, J.; Herres, N.; Fuchs, F.; Serries, D.; Grietens, B.; Németh, S.; Hoof, C. Van; Borghs, G.
1998-07-01
The structural properties of InAs/(GaIn)Sb and (InGa)As/GaSb superlattices (SLs), grown by solid-source molecular-beam epitaxy on (0 0 1) GaAs substrates using a strain relaxed GaSb or InAs buffer layer or directly on (0 0 1) InAs substrates, were analyzed by high-resolution X-ray diffraction and Raman spectroscopy. The residual strain within the SL was found to depend critically on the type of interface bonds, which can be either InSb- or GaAs-like. Thus, to achieve lattice matching to the buffer layer or substrate by strain compensation within the SL stack, the controlled formation of the interface bonds is vital. On the other hand, minimization of the residual strain is shown to be a prerequisite for achieving a high photoluminescence yield and high responsivities for InAs/(GaIn)Sb SL based IR detectors.
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
2016-01-01
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/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. PMID:26853933
NASA Astrophysics Data System (ADS)
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
2016-02-01
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.
OCReP: An Optimally Conditioned Regularization for pseudoinversion based neural training.
Cancelliere, Rossella; Gai, Mario; Gallinari, Patrick; Rubini, Luca
2015-11-01
In this paper we consider the training of single hidden layer neural networks by pseudoinversion, which, in spite of its popularity, is sometimes affected by numerical instability issues. Regularization is known to be effective in such cases, so that we introduce, in the framework of Tikhonov regularization, a matricial reformulation of the problem which allows us to use the condition number as a diagnostic tool for identification of instability. By imposing well-conditioning requirements on the relevant matrices, our theoretical analysis allows the identification of an optimal value for the regularization parameter from the standpoint of stability. We compare with the value derived by cross-validation for overfitting control and optimization of the generalization performance. We test our method for both regression and classification tasks. The proposed method is quite effective in terms of predictivity, often with some improvement on performance with respect to the reference cases considered. This approach, due to analytical determination of the regularization parameter, dramatically reduces the computational load required by many other techniques. PMID:26318638
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. PMID:26104115
NASA Astrophysics Data System (ADS)
Takeda, Norio
We verified the generalization ability of the response surfaces of artificial neural networks (NNs), and that the surfaces could be applied to an engineering-design problem. A Bayesian framework to regularize NNs, which was proposed by Gull and Skilling, can be used to generate NN response surfaces with excellent generalization ability, i.e., to determine the regularizing constants in an objective function minimized during NN learning. This well-generalized NN might be useful to find an optimal solution in the process of response surface methodology (RSM). We, therefore, describe three rules based on the Bayesian framework to update the regularizing constants, utilizing these rules to generate NN response surfaces with noisy teacher data drawn from a typical unimodal or multimodal function. Good generalization ability was achieved with regularized NN response surfaces, even though an update rule including trace evaluation failed to determine the regularizing constants regardless of the response function. We, next, selected the most appropriate update rule, which included eigenvalue evaluation, and then the NN response surface regularized using the update rule was applied to finding the optimal solution to an illustrative engineering-design problem. The NN response surface did not fit the noise in the teacher data, and consequently, it could effectively be used to achieve a satisfactory solution. This may increase the opportunities for using NN in the process of RSM.
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.
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.
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. PMID:25933101
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. PMID:25933101
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 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.
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.
Neural network river forecasting through baseflow separation and binary-coded swarm optimization
NASA Astrophysics Data System (ADS)
Taormina, Riccardo; Chau, Kwok-Wing; Sivakumar, Bellie
2015-10-01
The inclusion of expert knowledge in data-driven streamflow modeling is expected to yield more accurate estimates of river quantities. Modular models (MMs) designed to work on different parts of the hydrograph are preferred ways to implement such approach. Previous studies have suggested that better predictions of total streamflow could be obtained via modular Artificial Neural Networks (ANNs) trained to perform an implicit baseflow separation. These MMs fit separately the baseflow and excess flow components as produced by a digital filter, and reconstruct the total flow by adding these two signals at the output. The optimization of the filter parameters and ANN architectures is carried out through global search techniques. Despite the favorable premises, the real effectiveness of such MMs has been tested only on a few case studies, and the quality of the baseflow separation they perform has never been thoroughly assessed. In this work, we compare the performance of MM against global models (GMs) for nine different gaging stations in the northern United States. Binary-coded swarm optimization is employed for the identification of filter parameters and model structure, while Extreme Learning Machines, instead of ANN, are used to drastically reduce the large computational times required to perform the experiments. The results show that there is no evidence that MM outperform global GM for predicting the total flow. In addition, the baseflow produced by the MM largely underestimates the actual baseflow component expected for most of the considered gages. This occurs because the values of the filter parameters maximizing overall accuracy do not reflect the geological characteristics of the river basins. The results indeed show that setting the filter parameters according to expert knowledge results in accurate baseflow separation but lower accuracy of total flow predictions, suggesting that these two objectives are intrinsically conflicting rather than compatible.
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.
Optimization of the Blank Holder Force Using the Neural Network Algorithm
NASA Astrophysics Data System (ADS)
Albut, A.; Ciubotaru, V.; Radu, C.; Olaru, I.
2011-08-01
In case of sheet metal forming the main dimensional errors are caused by the springback phenomena. The present work deals with numerical simulation related to draw bending and springback of U-shaped parts. The current paper is trying to prove out the important role of the blank holder force variation during the forming process. The Dynaform 5.6 software was used to simulate the forming process, in which the blank holder force varies linearly in four steps between 20 and 50 kN. The factorial simulations test plan was made using the Design Experts 7.0 software and 72 simulations were necessarily to cover completely the variation domain. The part obtained after each simulation is analyzed and measured to quantify the errors caused by springback. Parameters as: angle between flange and sidewall, angle between sidewall and part bottom, chamfer radius between part bottom and sidewall or chamfer radius between sidewall and flange are recorded in a data base. The initial simulations plan together with the generated data base is loaded in a neural network software called NeuroSolution 5. The presented optimization method is a good method to reduce the springback effect. The inconvenient of this method is the large number of simulations tests that must be done and the large amount of data necessarily as input for the NeuroSolution software.
A neural network-based optimization algorithm for the weapon-target assignment problem
Wacholder, E.
1989-02-01
A neural network-based algorithm was developed for the Weapon-Target Assignment Problem (WTAP) in Ballistic Missile Defense (BMD). An optimal assignment policy is one which allocates targets to weapon platforms such that the total expected leakage value of targets surviving the defense is minimized. This involves the minimization of a non-linear objective function subject to inequality constraints specifying the maximum number of interceptors available to each platform and the maximum number of interceptors allowed to be fired at each target as imposed by the Battle Management/Command Control and Communications (BM/C/sup 3/) system. The algorithm consists of solving a system of ODEs trajectories and variables. Simulations of the algorithm on PC and VAX computers were carried out using a simple numerical scheme. In all the battle instances tested, the algorithm has proven to be stable and to converge to solutions very close to global optima. The time to achieve convergence was consistently less than the time constant of the network's processing elements (neurons). This implies that fast solutions can be realized if the algorithm is implemented in hardware circuits. Three series of battle scenarios are analyzed and discussed in this report. Input data and results are presented in detail. The main advantage of this algorithm is that it can be adapted to either a special-purpose hardware circuit or a general-purpose concurrent machine to yield fast and accurate solutions to difficult decision problems. 40 refs., 8 figs., 8 tabs.
Optimal design of 2D digital filters based on neural networks
NASA Astrophysics Data System (ADS)
Wang, Xiao-hua; He, Yi-gang; Zheng, Zhe-zhao; Zhang, Xu-hong
2005-02-01
Two-dimensional (2-D) digital filters are widely useful in image processing and other 2-D digital signal processing fields,but designing 2-D filters is much more difficult than designing one-dimensional (1-D) ones.In this paper, a new design approach for designing linear-phase 2-D digital filters is described,which is based on a new neural networks algorithm (NNA).By using the symmetry of the given 2-D magnitude specification,a compact express for the magnitude response of a linear-phase 2-D finite impulse response (FIR) filter is derived.Consequently,the optimal problem of designing linear-phase 2-D FIR digital filters is turned to approximate the desired 2-D magnitude response by using the compact express.To solve the problem,a new NNA is presented based on minimizing the mean-squared error,and the convergence theorem is presented and proved to ensure the designed 2-D filter stable.Three design examples are also given to illustrate the effectiveness of the NNA-based design approach.
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. PMID:27127499
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. PMID:27127499
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
GaAs Refractive Index Dependence On Carrier Density and Optimizing Terahertz Devices
NASA Astrophysics Data System (ADS)
Kim, Christopher; Wu, Dong Ho; Graber, Benjamin
GaAs is used for various applications, including high speed transistors, high-efficiency photovoltaic cells, electro-optics and terahertz (THz) emitters and detectors. To date, information on the refractive index of GaAs is available only over a limited wave spectrum of 0.2-17um, where the refractive index varies from 1.3 to 5.0. As detailed information on the refractive index of GaAs at THz frequencies is not available or inadequate for our effort to develop an improved GaAs-based THz emitter, we experimentally investigated the behavior of the refractive index of GaAs for different charge carrier densities, especially with or without the presence of surface plasma. Using a Time Domain THz Spectrometer, which is capable of measuring THz pulses containing a wave spectrum over 100-3000um with a time accuracy better than 6 femtoseconds, we measured the delay of THz pulses traversing through a GaAs substrate of known thickness while modulating the charge carrier concentration. From the experimental data we estimated the refractive index for THz frequencies to vary from 3.5 to 3.8 for different charge carrier concentrations. We will discuss details of our experiments and implications of our experimental results, especially for our GaAs-based THz devices.
Budilova, E.V.; Terekhin, A.T.; Chepurnov, S.A.
1995-03-01
A hypothetical neural scheme is proposed that ensures efficient decision making by an animal searching for food in a maze. Only the general structure of the network is fixed; its quantitative characteristics are found by numerical optimization that simulates the process of natural selection. Selection is aimed at maximization of the expected number of descendants, which is directly related to the energy stored during the reproductive cycle. The main parameters to be optimized are the increments of the interneuronal links. and the working-memory constants.
NASA Astrophysics Data System (ADS)
Budilova, E. V.; Terekhin, A. T.; Chepurnov, S. A.
1994-09-01
A hypothetical neural scheme is proposed that ensures efficient decision making by an animal searching for food in a maze. Only the general structure of the network is fixed; its quantitative characteristics are found by numerical optimization that simulates the process of natural selection. Selection is aimed at maximization of the expected number of descendants, which is directly related to the energy stored during the reproductive cycle. The main parameters to be optimized are the increments of the interneuronal links and the working-memory constants.
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
Cervera, C.; Rodriguez, J. B.; Perez, J. P.; Aiet-Kaci, H.; Chaghi, R.; Christol, P.; Konczewicz, L.; Contreras, S.
2009-08-01
In this communication we report on electrical properties of nonintentionally doped (nid) type II InAs/GaSb superlattice grown by molecular beam epitaxy. We present a simple technological process which, thanks to the suppression of substrate, allows direct Hall measurement on superlattice structures grown on conductive GaSb substrate. Two samples were used to characterize the transport: one grown on a semi-insulating GaAs substrate and another grown on n-GaSb substrate where a etch stop layer was inserted to remove the conductive substrate. Mobilities and carrier concentrations have been measured as a function of temperature (77-300 K), and compared with capacitance-voltage characteristic at 80 K of a photodiode comprising a similar nid superlattice.
4x4 Individually Addressable InGaAs APD Arrays Optimized for Photon Counting Applications
NASA Technical Reports Server (NTRS)
Gu, Y.; Wu, X.; Wu, S.; Choa, F. S.; Yan, F.; Shu, P.; Krainak, M.
2007-01-01
InGaAs APDs with improved photon counting characteristics were designed and fabricated and their performance improvements were observed. Following the results, a 4x4 individually addressable APD array was designed, fabricated, and results are reported.
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. PMID:25415951
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. PMID:26367382
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.
Yoo, Sung-Hoon; Oh, Sung-Kwun; Pedrycz, Witold
2015-09-01
In this study, we propose a hybrid method of face recognition by using face region information extracted from the detected face region. In the preprocessing part, we develop a hybrid approach based on the Active Shape Model (ASM) and the Principal Component Analysis (PCA) algorithm. At this step, we use a CCD (Charge Coupled Device) camera to acquire a facial image by using AdaBoost and then Histogram Equalization (HE) is employed to improve the quality of the image. ASM extracts the face contour and image shape to produce a personal profile. Then we use a PCA method to reduce dimensionality of face images. In the recognition part, we consider the improved Radial Basis Function Neural Networks (RBF NNs) to identify a unique pattern associated with each person. The proposed RBF NN architecture consists of three functional modules realizing the condition phase, the conclusion phase, and the inference phase completed with the help of fuzzy rules coming in the standard 'if-then' format. In the formation of the condition part of the fuzzy rules, the input space is partitioned with the use of Fuzzy C-Means (FCM) clustering. In the conclusion part of the fuzzy rules, the connections (weights) of the RBF NNs are represented by four kinds of polynomials such as constant, linear, quadratic, and reduced quadratic. The values of the coefficients are determined by running a gradient descent method. The output of the RBF NNs model is obtained by running a fuzzy inference method. The essential design parameters of the network (including learning rate, momentum coefficient and fuzzification coefficient used by the FCM) are optimized by means of Differential Evolution (DE). The proposed P-RBF NNs (Polynomial based RBF NNs) are applied to facial recognition and its performance is quantified from the viewpoint of the output performance and recognition rate. PMID:26163042
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. PMID:25330496
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)
Zhu, Di
2011-12-01
-current efficiency and reduced efficiency droop. Compared with 4-QB-doped LEDs, 1-QB-doped LEDs show a 37.5% increase in light-output power at high currents. Consistent with the measurements, simulation shows a shift of radiative recombination among the MQWs and a reduced electron leakage current into the p-type GaN when fewer QBs are doped. The results can be attributed to a more symmetric carrier transport and uniform carrier distribution which help to reduce electron leakage and thus reduce the efficiency droop. In this dissertation, artificial evolution is introduced to the LED optimization process which combines a genetic algorithm (GA) and device-simulation software. We show that this approach is capable of generating novel concepts in designing and optimizing LED devices. Application of the GA to the QB-doping in the MQWs yields optimized structures which is consistent with the tailored QB doping experiments. Application of the GA to the EBL region suggests a novel structure with an inverted sheet charge at the spacer-EBL interface. The resulting repulsion of electrons can significantly reduce electron leakage and enhance the efficiency. Finally, dual-wavelength LEDs, which have two types of quantum wells (QWs) emitting at two different wavelengths, are experimentally characterized and compared with numerical simulations. These dual-wavelength LEDs allow us to determine which QW emits most of the light. An experimental observation and a quantitative analysis of the radiative recombination shift within the MQW active region are obtained. In addition, an injection-current dependence of the radiative recombination shift is predicted by numerical simulations and indeed observed in dual-wavelength LEDs. This injection-current dependence of the radiative recombination distribution can be explained very well by incorporating quantum-mechanical tunneling of carriers into and through the QBs into to the classical drift-diffusion model. In summary, using the LEDs with tailored QB
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
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%.
Ghai, Aanchal; Singh, Baljinder; Panwar Hazari, Puja; Schultz, Michael K; Parmar, Ambika; Kumar, Pardeep; Sharma, Sarika; Dhawan, Devinder; Kumar Mishra, Anil
2015-11-01
The present study describes the optimization of (68)Ga radiolabeling with PAMAM dendrimer-DOTA conjugate. A conjugate (PAMAM-DOTA) concentration of 11.69µM, provided best radiolabeling efficiency of more than 93.0% at pH 4.0, incubation time of 30.0min and reaction temperature ranging between 90 and 100°C. The decay corrected radiochemical yield was found to be 79.4±0.01%. The radiolabeled preparation ([(68)Ga]-DOTA-PAMAM-D) remained stable (radiolabeling efficiency of 96.0%) at room temperature and in serum for up to 4-h. The plasma protein binding was observed to be 21.0%. After intravenous administration, 50.0% of the tracer cleared from the blood circulation by 30-min and less than 1.0% of the injected activity remained in blood by 1.0h. The animal biodistribution studies demonstrated that the tracer excretes through the kidneys and about 0.33% of the %ID/g accumulated in the tumor at 1h post injection. The animal organ's biodistribution data was supported by animal PET imaging showing good 'non-specific' tracer uptake in tumor and excretion is primarily through kidneys. Additionally, DOTA-PAMAM-D conjugation with αVβ3 receptors targeting peptides and drug loading on the dendrimers may improve the specificity of the (68)Ga labeled product for imaging and treating angiogenesis respectively. PMID:26232562
Li, Zhijun; Ge, Shuzhi Sam; Liu, Sibang
2014-08-01
This paper investigates optimal feet forces' distribution and control of quadruped robots under external disturbance forces. First, we formulate a constrained dynamics of quadruped robots and derive a reduced-order dynamical model of motion/force. Consider an external wrench on quadruped robots; the distribution of required forces and moments on the supporting legs of a quadruped robot is handled as a tip-point force distribution and used to equilibrate the external wrench. Then, a gradient neural network is adopted to deal with the optimized objective function formulated as to minimize this quadratic objective function subjected to linear equality and inequality constraints. For the obtained optimized tip-point force and the motion of legs, we propose the hybrid motion/force control based on an adaptive neural network to compensate for the perturbations in the environment and approximate feedforward force and impedance of the leg joints. The proposed control can confront the uncertainties including approximation error and external perturbation. The verification of the proposed control is conducted using a simulation. PMID:25050944
Dierks, Travis; Thumati, Balaje T; Jagannathan, S
2009-01-01
The optimal control of linear systems accompanied by quadratic cost functions can be achieved by solving the well-known Riccati equation. However, the optimal control of nonlinear discrete-time systems is a much more challenging task that often requires solving the nonlinear Hamilton-Jacobi-Bellman (HJB) equation. In the recent literature, discrete-time approximate dynamic programming (ADP) techniques have been widely used to determine the optimal or near optimal control policies for affine nonlinear discrete-time systems. However, an inherent assumption of ADP requires the value of the controlled system one step ahead and at least partial knowledge of the system dynamics to be known. In this work, the need of the partial knowledge of the nonlinear system dynamics is relaxed in the development of a novel approach to ADP using a two part process: online system identification and offline optimal control training. First, in the system identification process, a neural network (NN) is tuned online using novel tuning laws to learn the complete plant dynamics so that a local asymptotic stability of the identification error can be shown. Then, using only the learned NN system model, offline ADP is attempted resulting in a novel optimal control law. The proposed scheme does not require explicit knowledge of the system dynamics as only the learned NN model is needed. The proof of convergence is demonstrated. Simulation results verify theoretical conjecture. PMID:19596551
Zhang, Yan-jun; Liu, Wen-zhe; Fu, Xing-hu; Bi, Wei-hong
2015-10-01
According to the high precision extracting characteristics of scattering spectrum in Brillouin optical time domain reflection optical fiber sensing system, this paper proposes a new algorithm based on flies optimization algorithm with adaptive mutation and generalized regression neural network. The method takes advantages of the generalized regression neural network which has the ability of the approximation ability, learning speed and generalization of the model. Moreover, by using the strong search ability of flies optimization algorithm with adaptive mutation, it can enhance the learning ability of the neural network. Thus the fitting degree of Brillouin scattering spectrum and the extraction accuracy of frequency shift is improved. Model of actual Brillouin spectrum are constructed by Gaussian white noise on theoretical spectrum, whose center frequency is 11.213 GHz and the linewidths are 40-50, 30-60 and 20-70 MHz, respectively. Comparing the algorithm with the Levenberg-Marquardt fitting method based on finite element analysis, hybrid algorithm particle swarm optimization, Levenberg-Marquardt and the least square method, the maximum frequency shift error of the new algorithm is 0.4 MHz, the fitting degree is 0.991 2 and the root mean square error is 0.024 1. The simulation results show that the proposed algorithm has good fitting degree and minimum absolute error. Therefore, the algorithm can be used on distributed optical fiber sensing system based on Brillouin optical time domain reflection, which can improve the fitting of Brillouin scattering spectrum and the precision of frequency shift extraction effectively. PMID:26904844
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. PMID:25372405
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.
Songmuang, R; Giang, Le Thuy Thanh; Bleuse, J; Den Hertog, M; Niquet, Y M; Dang, Le Si; Mariette, H
2016-06-01
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. PMID:27081785
NASA Astrophysics Data System (ADS)
Robert, Stéphane; Mure-Ravaud, Alain; Thiria, Sylvie; Yacoub, Méziane; Badran, Fouad
2004-08-01
The characterization of gratings with small period-to-wavelength ratios can be achieved by solving the inverse problem of the diffraction. The use of a neural network has shown several advantages: it is a non-destructive, non-local and non-invasive method. However, although the calculation of results is instantaneous, the neural characterizations already published require the measurement of many diffracted intensities and can so need a long measurement time. We present, in this paper, a neural selection process called heuristic variable selection. This method reduces the number of diffractive efficiencies allowing a correct reconstruction of the profile shape according to an expected accuracy. In the same way, the non-redundancy of the data composing the optical signature is ensured. We relate a 1-μm period grating etched in silicon which could be characterized with only six measurements when a trapezoidal profile shape is assumed.
Optimization of inductively coupled plasma deep etching of GaN and etching damage analysis
NASA Astrophysics Data System (ADS)
Qiu, Rongfu; Lu, Hai; Chen, Dunjun; Zhang, Rong; Zheng, Youdou
2011-01-01
Inductively coupled plasma (ICP) etching of GaN with an etching depth up to 4 μm is systemically studied by varying ICP power, RF power and chamber pressure, respectively, which results in etch rates ranging from ∼370 nm/min to 900 nm/min. The surface morphology and damages of the etched surface are characterized by optical microscope, scanning electron microscope, atomic force microscopy, cathodoluminescence mapping and photoluminescence (PL) spectroscopy. Sub-micrometer-scale hexagonal pits and pillars originating from part of the structural defects within the original GaN layer are observed on the etched surface. The density of these surface features varies with etching conditions. Considerable reduction of PL band-edge emission from the etched GaN surface indicates that high-density non-radiative recombination centers are created by ICP etching. The density of these non-radiative recombination centers is found largely dependent on the degree of physical bombardments, which is a strong function of the RF power applied. Finally, a low-surface-damage etch recipe with high ICP power, low RF power, high chamber pressure is suggested.
Design and optimization of dielectric optical coatings for GaN based high bright LEDs
NASA Astrophysics Data System (ADS)
Wang, Xiaodong; Li, Yan; Yang, Hua; Yi, Xiaoyan; Wang, Liangchen; Wang, Guohong; Yang, Fuhua; Li, Jinmin
2008-03-01
Different types of dielectric optical coatings for GaN based high bright LEDs were designed and discussed. The optical coatings included the anti-reflection (AR) coating, high-reflection (HR) coating, and omni-directional high reflection coating. Main materials for the optical coatings were dielectric materials such as SiO II, Ta IIO 5 and Al IIO 3, which were different from the metallic reflector such as Ag usually used now. For the application of anti-reflection coating in GaN LEDs, it was introduced into the design of transparent electrodes with transparent materials such as ITO to form combined transparent electrodes. With the design of P, N transparent electrodes using the AR coating and ITO for GaN LEDs, the extraction efficiency was improved by about 15% experimentally. For the dielectric high-reflection coating, it has higher reflectivity and lower absorption than the metal reflector, and it was supposed to improve the extraction efficiency obviously. While the dielectric omni-directional reflection coating using dielectric materials was also designed and discussed in this article, since which was anticipated to improve the extraction efficiency furthermore. Using SiO II and Ta IIO 5, the average reflectivity of a design of all dielectric omni-directional high reflection coating on the sapphire surface was over 94%.
NASA Astrophysics Data System (ADS)
Taher, Seyed Abbas; Hasani, Mohammad; Karimian, Ali
2011-02-01
A genetic algorithm (GA) is proposed for simultaneous power quality improvement, optimal placement and sizing of fixed capacitor banks in radial distribution networks with nonlinear loads and distributed generation (DG) imposing voltage-current harmonics. In distribution systems, nonlinear loads and DGs are often considered as harmonic sources. For optimizing capacitor placement and sizing in the distribution system, objective function includes the cost of power losses, energy losses and capacitor banks. At the same time, constraints include voltage limits, number/size of installed capacitors (at each bus) and the power quality limits of standard IEEE-519. In this study, new fitness function is used to solve the constrained optimization problem with discrete variables. Simulation results for two IEEE distorted networks (18-bus and 33-bus test systems) are presented and solutions of the proposed method are compared with those of previous methods described in the literature. The main contribution of this paper is computing the (near) global solution with a lower probability of getting stuck at a local optimum and weak dependency on initial conditions, while avoiding numerical problems in large systems. Results show that proposed method could be effectively used for optimal capacitor placement and sizing in distorted distribution systems.
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. PMID:26211074
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. PMID:27595102
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. PMID:22588610
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.
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.
Prediction of skin sensitization potential using D-optimal design and GA-kNN classification methods.
Gunturi, S B; Theerthala, S S; Patel, N K; Bahl, J; Narayanan, R
2010-04-01
Modelling of skin sensitization data of 255 diverse compounds and 450 calculated descriptors was performed to develop global predictive classification models that are applicable to whole chemical space. With this aim, we employed two automated procedures, (a) D-optimal design to select optimal members of the training and test sets and (b) k-Nearest Neighbour classification (kNN) method along with Genetic Algorithms (GA-kNN Classification) to select significant and independent descriptors in order to build the models. This methodology helped us to derive multiple models, M1-M5, that are stable and robust. The best among them, model M1 (CCR(train) = 84.3%, CCR(test) = 87.2% and CCR(ext) = 80.4%), is based on six neighbours and nine descriptors and further suggests that: (a) it is stable and robust and performs better than the reported models in literature, and (b) the combination of D-optimal design and GA-kNN classification approach is a very promising approach. Consensus prediction based on the models M1-M5 improved the CCR of training, test and external validation datasets by 3.8%, 4.45% and 3.85%, respectively, over M1. From the analysis of the physical meaning of the selected descriptors, it is inferred that the skin sensitization potential of small organic compounds can be accurately predicted using calculated descriptors that code for the following fundamental properties: (i) lipophilicity, (ii) atomic polarizability, (iii) shape, (iii) electrostatic interactions, and (iv) chemical reactivity. PMID:20544553
Zhang, Kedong; Zhang, Baiyu; Chen, Bing; Jing, Liang; Zhu, Zhiwen; Kazemi, Khoshrooz
2016-08-15
The hydrolyzed protein derived from seafood waste is regarded as a premium and low-cost nitrogen source for microbial growth. In this study, optimization of enzymatic shrimp waste hydrolyzing process was investigated. The degree of hydrolysis (DH) with four processing variables including enzyme/substrate ratio (E/S), hydrolysis time, initial pH value and temperature, were monitored. The DH values were used for response surface methodology (RSM) optimization through central composite design (CCD) and for training artificial neural network (ANN) to make a process prediction. Results indicated that the optimum levels of variables are: E/S ratio at 1.64%, hydrolysis time at 3.59h, initial pH at 9 and temperature at 52.57°C. Hydrocarbon-degrading bacteria Bacillus subtilis N3-1P was cultivated using different DHs of hydrolysate. The associated growth curves were generated. The research output facilitated effective shrimp waste utilization. PMID:27312986
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.
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. PMID:27243606
Hall, L Mark; Hill, Dennis W; Menikarachchi, Lochana C; Chen, Ming-Hui; Hall, Lowell H; Grant, David F
2015-01-01
Background 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. Methodology 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. Conclusion 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. PMID:25966007
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. PMID:27424214
[Optimization of pellet formulation with the help of artificial neural networks].
Kása, Péter; Sovány, Tamás; Hódi, Klára
2007-01-01
The authors demonstrate the essence and the application possibility of artificial neural networks in the formulation of pharmaceutical preparations. They draw attention to that the use of ANN the data processing will speed up and more accurate which will cause the decrease of the preliminary investigations and the amounts of the materials. PMID:17933271
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.
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
Šiljić Tomić, Aleksandra N; Antanasijević, Davor Z; Ristić, Mirjana Đ; Perić-Grujić, Aleksandra A; Pocajt, Viktor V
2016-05-01
This paper describes the application of artificial neural network models for the prediction of biological oxygen demand (BOD) levels in the Danube River. Eighteen regularly monitored water quality parameters at 17 stations on the river stretch passing through Serbia were used as input variables. The optimization of the model was performed in three consecutive steps: firstly, the spatial influence of a monitoring station was examined; secondly, the monitoring period necessary to reach satisfactory performance was determined; and lastly, correlation analysis was applied to evaluate the relationship among water quality parameters. Root-mean-square error (RMSE) was used to evaluate model performance in the first two steps, whereas in the last step, multiple statistical indicators of performance were utilized. As a result, two optimized models were developed, a general regression neural network model (labeled GRNN-1) that covers the monitoring stations from the Danube inflow to the city of Novi Sad and a GRNN model (labeled GRNN-2) that covers the stations from the city of Novi Sad to the border with Romania. Both models demonstrated good agreement between the predicted and actually observed BOD values. PMID:27094057