Home About us Contact
|
Home About us Contact | ||
|
|
||
Neural Network Models (neural + network_models)
Kinds of Neural Network Models Selected AbstractsDynamic On-Line Reoptimization Control of a Batch MMA Polymerization Reactor Using Hybrid Neural Network ModelsCHEMICAL ENGINEERING & TECHNOLOGY (CET), Issue 9 2004Y. Tian Abstract A hybrid neural network model based on-line reoptimization control strategy is developed for a batch polymerization reactor. To address the difficulties in batch polymerization reactor modeling, the hybrid neural network model contains a simplified mechanistic model covering material balance assuming perfect temperature control, and recurrent neural networks modeling the residuals of the simplified mechanistic model due to imperfect temperature control. This hybrid neural network model is used to calculate the optimal control policy. A difficulty in the optimal control of batch polymerization reactors is that the optimization effort can be seriously hampered by unknown disturbances such as reactive impurities and reactor fouling. With the presence of an unknown amount of reactive impurities, the off-line calculated optimal control profile will be no longer optimal. To address this issue, a strategy combining on-line reactive impurity estimation and on-line reoptimization is proposed in this paper. The amount of reactive impurities is estimated on-line during the early stage of a batch by using a neural network based inverse model. Based on the estimated amount of reactive impurities, on-line reoptimization is then applied to calculate the optimal reactor temperature profile for the remaining time period of the batch reactor operation. This approach is illustrated on the optimization control of a simulated batch methyl methacrylate polymerization process. [source] Short-term travel speed prediction models in car navigation systemsJOURNAL OF ADVANCED TRANSPORTATION, Issue 2 2006Seungjae Lee The objective of this study is the development of the short-term prediction models to predict average spot speeds of the subject location in the short-term periods of 5, 10 and 15 minutes respectively. In this study, field data were used to see the comparison of the predictability of Regression Analysis, ARIMA, Kalman Filtering and Neural Network models. These field data were collected from image processing detectors at the urban expressway for 17 hours including both peak and non-peak hours. Most of the results were reliable, but the results of models using Kalman Filtering and Neural Networks are more accurate and realistic than those of the others. [source] Model Reduction in Emulsion Polymerization Using Hybrid First Principles/Artificial Neural Networks Models, 2,MACROMOLECULAR THEORY AND SIMULATIONS, Issue 2 2005Gurutze Arzamendi Abstract Summary: A "series" hybrid model based on material balances and artificial neural networks to predict the evolution of weight average molecular weight, , in semicontinuous emulsion polymerization with long chain branching kinetics is presented. The core of the model is composed by two artificial neural networks (ANNs) that calculate polymerization rate, Rp, and instantaneous weight-average molecular weight, from reactor process variables. The subsequent integration of the material balances allowed to obtain the time evolution of conversion and , along the polymerization process. The accuracy of the proposed model under a wide range of conditions was assessed. The low computer-time load makes the hybrid model suitable for optimization strategies. Effect of the monomer feed rate on . [source] Neural network models to predict cation exchange capacity in arid regions of IranEUROPEAN JOURNAL OF SOIL SCIENCE, Issue 4 2005M. Amini Summary Design and analysis of land-use management scenarios requires detailed soil data. When such data are needed on a large scale, pedotransfer functions (PTFs) could be used to estimate different soil properties. Because existing regression-based PTFs for estimating cation exchange capacity (CEC) do not, in general, apply well to arid areas, this study was conducted (i) to evaluate the existing models and (ii) to develop neural network-based PTFs for predicting CEC in Aridisols of Isfahan in central Iran. As most researches have found a significant correlation between CEC and soil organic matter content (OM) and clay content, we also used these two variables for modelling of CEC. We tested several published PTFs and developed two neural network algorithms using multilayer perceptron and general regression neural networks based on a set of 170 soil samples. The data set was divided into two subsets for calibration and testing of the models. In general, the neural network-based models provided more reliable predictions than the regression-based PTFs. [source] A Review on Residence Time Distribution (RTD) in Food Extruders and Study on the Potential of Neural Networks in RTD ModelingJOURNAL OF FOOD SCIENCE, Issue 6 2002G. Ganjyal ABSTRACT: Residence time distribution and mean residence time depend on process variables, namely feed rate, screw speed, feed moisture content, barrel temperature, die temperature and die diameter. Flow in an extruder has been modeled by simulating residence time distribution, assuming the extruder to be a series of continuous-stirred-tank or plug-flow reactors. Others have developed relationships for mean residence time as functions of process variables. Better models can be developed using neural networks. As an example, data from the literature were used to model mean residence time as a function of process variables using statistical regression and neural networks. Neural network models performed better than regression models. [source] Neural Network Earnings per Share Forecasting Models: A Comparative Analysis of Alternative MethodsDECISION SCIENCES, Issue 2 2004Wei Zhang ABSTRACT In this paper, we present a comparative analysis of the forecasting accuracy of univariate and multivariate linear models that incorporate fundamental accounting variables (i.e., inventory, accounts receivable, and so on) with the forecast accuracy of neural network models. Unique to this study is the focus of our comparison on the multivariate models to examine whether the neural network models incorporating the fundamental accounting variables can generate more accurate forecasts of future earnings than the models assuming a linear combination of these same variables. We investigate four types of models: univariate-linear, multivariate-linear, univariate-neural network, and multivariate-neural network using a sample of 283 firms spanning 41 industries. This study shows that the application of the neural network approach incorporating fundamental accounting variables results in forecasts that are more accurate than linear forecasting models. The results also reveal limitations of the forecasting capacity of investors in the security market when compared to neural network models. [source] Prediction of biodegradation from the atom-type electrotopological state indicesENVIRONMENTAL TOXICOLOGY & CHEMISTRY, Issue 10 2001Jarmo Huuskonen Abstract A group contribution method based on atom-type electrotopological state indices for predicting the biodegradation of a diverse set of 241 organic chemicals is presented. Multiple linear regression and artificial neural networks were used to build the models using a training set of 172 compounds, for which the approximate time for ultimate biodegradation was estimated from the results of a survey of an expert panel. Derived models were validated by using a leave-25%-out method and against two test sets of 12 and 57 chemicals not included in the training set. The squared correlation coefficient (r2) for a linear model with 15 structural parameters was 0.76 for the training set and 0.68 for the test set of 12 molecules. The model predicted correctly the biodegradation of 48 chemicals in the test set of 57 molecules, for which biodegradability was presented as rapid or slow. The use of artificial neural networks gave better prediction for both test sets when the same set of parameters was tested as inputs in neural network simulations. The predictions of rapidly biodegradable chemicals were more accurate than the predictions of slowly bio-degradable chemicals for both the regression and neural network models. [source] Stepwise geographical traceability of virgin olive oils by chemical profiles using artificial neural network modelsEUROPEAN JOURNAL OF LIPID SCIENCE AND TECHNOLOGY, Issue 10 2009Diego L. García-González Abstract The geographical traceability of virgin olive oils implies the use of analytical methods that allow the identification of the origin of the oil and the authentication of the information boasted on the labels. In this work, the geographical identification of the virgin olive oils has been addressed by complete chemical characterisation of samples (64 compounds analysed by GC and HPLC) and the design of artificial neural network (ANN) models for each one of the levels of a proposed classification scheme. A high number of samples (687) from Spain, Italy and Portugal served as training and test sets for the ANN models. The highest classification level, focused on the grouping of samples by country, was achieved through analysis of fatty acids, with 99.9% of samples classified. Other levels (region, province, Protected Designations of Origin or PDO) were focused on Spanish oils and required additional series of compounds (sterols, alcohols, hydrocarbons) as well as the fatty acids to obtain classification rates higher than 90%. The classification of oils into different PDOs , the last and most difficult level of classification , showed the highest root mean square errors. The classification percentages, however, were still higher than 90% in the test set, which proves the application of the traceability methodology for a chemical verification of PDO claims. [source] Modified mixture of experts employing eigenvector methods and Lyapunov exponents for analysis of electroencephalogram signalsEXPERT SYSTEMS, Issue 4 2009Elif Derya ÜbeyliArticle first published online: 2 SEP 200 Abstract: The use of diverse features in detecting variability of electroencephalogram (EEG) signals is presented. The classification accuracies of the modified mixture of experts (MME), which was trained on diverse features, were obtained. Eigenvector methods (Pisarenko, multiple signal classification , MUSIC, and minimum-norm) were selected to generate the power spectral density estimates. The features from the power spectral density estimates and Lyapunov exponents of the EEG signals were computed and statistical features were calculated to depict their distribution. The statistical features, which were used for obtaining the diverse features of the EEG signals, were then input into the implemented neural network models for training and testing purposes. The present study demonstrated that the MME trained on the diverse features achieved high accuracy rates (total classification accuracy of the MME is 98.33%). [source] Neural network ensembles: combining multiple models for enhanced performance using a multistage approachEXPERT SYSTEMS, Issue 5 2004Shuang Yang Abstract: Neural network ensembles (sometimes referred to as committees or classifier ensembles) are effective techniques to improve the generalization of a neural network system. Combining a set of neural network classifiers whose error distributions are diverse can generate better results than any single classifier. In this paper, some methods for creating ensembles are reviewed, including the following approaches: methods of selecting diverse training data from the original source data set, constructing different neural network models, selecting ensemble nets from ensemble candidates and combining ensemble members' results. In addition, new results on ensemble combination methods are reported. [source] Short-term electric power load forecasting using feedforward neural networksEXPERT SYSTEMS, Issue 3 2004Heidar A. Malki Abstract: This paper presents the results of a study on short-term electric power load forecasting based on feedforward neural networks. The study investigates the design components that are critical in power load forecasting, which include the selection of the inputs and outputs from the data, the formation of the training and the testing sets, and the performance of the neural network models trained to forecast power load for the next hour and the next day. The experiments are used to identify the combination of the most significant parameters that can be used to form the inputs of the neural networks in order to reduce the prediction error. The prediction error is also reduced by predicting the difference between the power load of the next hour (day) and that of the present hour (day). This is a promising alternative to the commonly used approach of predicting the actual power load. The potential of the proposed method is revealed by its comparison with two existing approaches that utilize neural networks for electric power load forecasting. [source] Grid cells: The position code, neural network models of activity, and the problem of learningHIPPOCAMPUS, Issue 12 2008Peter E. Welinder Abstract We review progress on the modeling and theoretical fronts in the quest to unravel the computational properties of the grid cell code and to explain the mechanisms underlying grid cell dynamics. The goals of the review are to outline a coherent framework for understanding the dynamics of grid cells and their representation of space; to critically present and draw contrasts between recurrent network models of grid cells based on continuous attractor dynamics and independent-neuron models based on temporal interference; and to suggest open questions for experiment and theory. © 2008 Wiley-Liss, Inc. [source] Computational Modeling of Statistical Learning: Effects of Transitional Probability Versus Frequency and Links to Word LearningINFANCY, Issue 5 2010Daniel Mirman Statistical learning mechanisms play an important role in theories of language acquisition and processing. Recurrent neural network models have provided important insights into how these mechanisms might operate. We examined whether such networks capture two key findings in human statistical learning. In Simulation 1, a simple recurrent network (SRN) performed much like human learners: it was sensitive to both transitional probability and frequency, with frequency dominating early in learning and probability emerging as the dominant cue later in learning. In Simulation 2, an SRN captured links between statistical segmentation and word learning in infants and adults, and suggested that these links arise because phonological representations are more distinctive for syllables with higher transitional probability. Beyond simply simulating general phenomena, these models provide new insights into underlying mechanisms and generate novel behavioral predictions. [source] Optimizing object classification under ambiguity/ignorance: application to the credit rating problemINTELLIGENT SYSTEMS IN ACCOUNTING, FINANCE & MANAGEMENT, Issue 2 2005Malcolm J. Beynon A nascent technique for object classification is employed to exposit the classification of US banks to their financial strength ratings, presented by the Moody's Investors Services. The classification technique primarily utilized, called CaRBS (classification and ranking belief simplex), allows for the presence of ignorance to be inherent. The modern constrained optimization method, trigonometric differential evolution (TDE), is adopted to configure a CaRBS system. Two different objective functions are considered with TDE to measure the level of optimization achieved, which utilize differently the need to reduce ambiguity and/or ignorance inherently during the optimization process. The appropriateness of the CaRBS system to analyse incomplete data is also highlighted, with no requirement to impute any missing values or remove objects with missing values inherent. Comparative results are also presented using the well-known multivariate discriminant analysis and neural network models. The findings in this study identify a novel dimension to the issue of object classification optimization, with the discernment between the concomitant notions of ambiguity and ignorance. Copyright © 2005 John Wiley & Sons, Ltd. [source] Off-site monitoring systems for predicting bank underperformance: a comparison of neural networks, discriminant analysis, and professional human judgmentINTELLIGENT SYSTEMS IN ACCOUNTING, FINANCE & MANAGEMENT, Issue 3 2001Philip Swicegood This study compares the ability of discriminant analysis, neural networks, and professional human judgment methodologies in predicting commercial bank underperformance. Experience from the banking crisis of the 1980s and early 1990s suggest that improved prediction models are needed for helping prevent bank failures and promoting economic stability. Our research seeks to address this issue by exploring new prediction model techniques and comparing them to existing approaches. When comparing the predictive ability of all three models, the neural network model shows slightly better predictive ability than that of the regulators. Both the neural network model and regulators significantly outperform the benchmark discriminant analysis model's accuracy. These findings suggest that neural networks show promise as an off-site surveillance methodology. Factoring in the relative costs of the different types of misclassifications from each model also indicates that neural network models are better predictors, particularly when weighting Type I errors more heavily. Further research with neural networks in this field should yield workable models that greatly enhance the ability of regulators and bankers to identify and address weaknesses in banks before they approach failure. Copyright © 2001 John Wiley & Sons, Ltd. [source] Clustering with artificial neural networks and traditional techniquesINTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, Issue 4 2003G. Tambouratzis In this article, two clustering techniques based on neural networks are introduced. The two neural network models are the Harmony theory network (HTN) and the self-organizing logic neural network (SOLNN), both of which are characterized by parallel processing, a distributed architecture, and a large number of nodes. After describing their clustering characteristics and potential, a comparison to classical statistical techniques is performed. This comparison allows the creation of a correspondence between each neural network clustering technique and particular metrics as used by the corresponding statistical methods, which reflect the affinity of the clustered patterns. In particular, the HTN is found to perform the clustering task with an accuracy similar to the best statistical methods, while it is further capable of proposing an optimal number of groups into which the patterns may be clustered. On the other hand, the SOLNN combines a high clustering accuracy with the ability to cluster higher-dimensional patterns without a considerable increase in the processing time. © 2003 Wiley Periodicals, Inc. [source] Modeling power and intermodulation behavior of microwave transistors with unified small-signal/large-signal neural network modelsINTERNATIONAL JOURNAL OF RF AND MICROWAVE COMPUTER-AIDED ENGINEERING, Issue 4 2003F. Giannini Abstract This article presents a detailed procedure to learn a nonlinear model and its derivatives to as many orders as desired with multilayer perceptron (MLP) neural networks. A modular neural network modeling a nonlinear function and its derivatives is introduced. The method has been used for the extraction of the large-signal model of a power MESFET device, modeling the nonlinear relationship of drain-source current Ids as well as gate and drain charge Qg and Qd with respect to intrinsic voltages Vgs and Vds over the whole operational bias region. The neural models have been implemented into a user-defined nonlinear model of a commercial microwave simulator to predict output power performance as well as intermodulation distortion. The accuracy of the device model is verified by harmonic load-pull measurements. This neural network approach has demonstrated to predict nonlinear behavior with enough accuracy even if based only on first-order derivative information. © 2003 Wiley Periodicals, Inc. Int J RF and Microwave CAE 13: 276,284, 2003. [source] DYNAMIC MODELING OF RETORT PROCESSING USING NEURAL NETWORKSJOURNAL OF FOOD PROCESSING AND PRESERVATION, Issue 2 2002C. R. CHEN ABSTRACT Two neural network approaches , a moving-window and hybrid neural network , which combine neural network with polynomial regression models, were used for modeling F(t) and Qv(t) dynamic functions under constant retort temperature processing. The dynamic functions involved six variables: retort temperature (116,132C), thermal diffusivity (1.5,2.3 × 10,7m2/s), can radius (40,61 mm), can height (40,61 mm), and quality kinetic parameters z (15,39C) and D (150,250 min). A computer simulation designed for process calculations of food thermal processing systems was used to provide the fundamental data for training and generalization of ANN models. Training data and testing data were constructed by both second order central composite design and orthogonal array, respectively. The optimal configurations of ANN models were obtained by varying the number of hidden layers, number of neurons in hidden layer and learning runs, and a combination of learning rules and transfer function. Results demonstrated that both neural network models well described the F(t) and Qv(t) dynamic functions, but moving-window network had better modeling performance than the hybrid ANN models. By comparison of the configuration parameters, moving-window ANN models required more neurons in the hidden layer and more learning runs for training than the hybrid ANN models. [source] Building neural network models for time series: a statistical approachJOURNAL OF FORECASTING, Issue 1 2006Marcelo C. Medeiros Abstract This paper is concerned with modelling time series by single hidden layer feedforward neural network models. A coherent modelling strategy based on statistical inference is presented. Variable selection is carried out using simple existing techniques. The problem of selecting the number of hidden units is solved by sequentially applying Lagrange multiplier type tests, with the aim of avoiding the estimation of unidentified models. Misspecification tests are derived for evaluating an estimated neural network model. All the tests are entirely based on auxiliary regressions and are easily implemented. A small-sample simulation experiment is carried out to show how the proposed modelling strategy works and how the misspecification tests behave in small samples. Two applications to real time series, one univariate and the other multivariate, are considered as well. Sets of one-step-ahead forecasts are constructed and forecast accuracy is compared with that of other nonlinear models applied to the same series. Copyright © 2006 John Wiley & Sons, Ltd. [source] Unemployment variation over the business cycles: a comparison of forecasting modelsJOURNAL OF FORECASTING, Issue 7 2004Saeed Moshiri Abstract Asymmetry has been well documented in the business cycle literature. The asymmetric business cycle suggests that major macroeconomic series, such as a country's unemployment rate, are non-linear and, therefore, the use of linear models to explain their behaviour and forecast their future values may not be appropriate. Many researchers have focused on providing evidence for the non-linearity in the unemployment series. Only recently have there been some developments in applying non-linear models to estimate and forecast unemployment rates. A major concern of non-linear modelling is the model specification problem; it is very hard to test all possible non-linear specifications, and to select the most appropriate specification for a particular model. Artificial neural network (ANN) models provide a solution to the difficulty of forecasting unemployment over the asymmetric business cycle. ANN models are non-linear, do not rely upon the classical regression assumptions, are capable of learning the structure of all kinds of patterns in a data set with a specified degree of accuracy, and can then use this structure to forecast future values of the data. In this paper, we apply two ANN models, a back-propagation model and a generalized regression neural network model to estimate and forecast post-war aggregate unemployment rates in the USA, Canada, UK, France and Japan. We compare the out-of-sample forecast results obtained by the ANN models with those obtained by several linear and non-linear times series models currently used in the literature. It is shown that the artificial neural network models are able to forecast the unemployment series as well as, and in some cases better than, the other univariate econometrics time series models in our test. Copyright © 2004 John Wiley & Sons, Ltd. [source] Predicting LDC debt rescheduling: performance evaluation of OLS, logit, and neural network modelsJOURNAL OF FORECASTING, Issue 8 2001Douglas K. Barney Abstract Empirical studies in the area of sovereign debt have used statistical models singularly to predict the probability of debt rescheduling. Unfortunately, researchers have made few efforts to test the reliability of these model predictions or to identify a superior prediction model among competing models. This paper tested neural network, OLS, and logit models' predictive abilities regarding debt rescheduling of less developed countries (LDC). All models predicted well out-of-sample. The results demonstrated a consistent performance of all models, indicating that researchers and practitioners can rely on neural networks or on the traditional statistical models to give useful predictions. Copyright © 2001 John Wiley & Sons, Ltd. [source] PREDICTION OF MECHANICAL PROPERTIES OF CUMIN SEED USING ARTIFICIAL NEURAL NETWORKSJOURNAL OF TEXTURE STUDIES, Issue 1 2010M.H. SAIEDIRAD ABSTRACT In this paper, two artificial neural networks (ANNs) are applied to acquire the relationship between the mechanical properties and moisture content of cumin seed, using the data of quasi-static loading test. In establishing these relationship, the moisture content, seed size, loading rate and seed orientation were taken as the inputs of both models. The force and energy required for fracturing of cumin seed, under quasi-static loading were taken as the outputs of two models. The activation function in the output layer of models obeyed a linear output, whereas the activation function in the hidden layers were in the form of a sigmoid function. Adjusting ANN parameters such as learning rate and number of neurons and hidden layers affected the accuracy of force and energy prediction. Comparison of the predicted and experimented data showed that the ANN models used to predict the relationships of mechanical properties of cumin seed have a good learning precision and good generalization, because the root mean square errors of the predicated data by ANNs were rather low (4.6 and 7.7% for the force and energy, respectively). PRACTICAL APPLICATIONS Cumin seed is generally used as a food additive in the form of powder for imparting flavor to different food preparations and for a variety of medicinal properties. Physical properties of cumin seeds are essential for the design of equipment for handling, harvesting, aeration, drying, storing, grinding and processing. For powder preparation especially the fracture behavior of the seeds are essential. These properties are affected by numerous factors such as size, form and moisture content of the grain and deformation speed. A neural network model was developed that can be used to predict the relationships of mechanical properties. Artificial neural network models are powerful empirical models approach, which can be compared with mathematical models. [source] Characterization of Mixtures Part 1: Prediction of Infinite-Dilution Activity Coefficients Using Neural Network-Based QSPR ModelsMOLECULAR INFORMATICS, Issue 11-12 2008Subhash Ajmani Abstract The major problem in building QSAR/QSPR models for mixtures lies in their characterization. It has been shown that it is possible to construct QSPR models for the density of binary liquid mixtures using simple mole fraction weighted physicochemical descriptors. Such parameters are unsatisfactory; however, from the point of view of interpretation of the resultant models. In this paper, an alternative mechanism-based approach to the characterization of mixtures has been investigated. It has been shown that while it is not possible to build significant linear models using these descriptors, it has been possible to construct satisfactory artificial neural network models. The performance of these models and the importance of the individual descriptors are discussed. [source] Weather-based prediction of anthracnose severity using artificial neural network modelsPLANT PATHOLOGY, Issue 4 2004S. Chakraborty Data were collected and analysed from seven field sites in Australia, Brazil and Colombia on weather conditions and the severity of anthracnose disease of the tropical pasture legume Stylosanthes scabra caused by Colletotrichum gloeosporioides. Disease severity and weather data were analysed using artificial neural network (ANN) models developed using data from some or all field sites in Australia and/or South America to predict severity at other sites. Three series of models were developed using different weather summaries. Of these, ANN models with weather for the day of disease assessment and the previous 24 h period had the highest prediction success, and models trained on data from all sites within one continent correctly predicted disease severity in the other continent on more than 75% of days; the overall prediction error was 21·9% for the Australian and 22·1% for the South American model. Of the six cross-continent ANN models trained on pooled data for five sites from two continents to predict severity for the remaining sixth site, the model developed without data from Planaltina in Brazil was the most accurate, with >85% prediction success, and the model without Carimagua in Colombia was the least accurate, with only 54% success. In common with multiple regression models, moisture-related variables such as rain, leaf surface wetness and variables that influence moisture availability such as radiation and wind on the day of disease severity assessment or the day before assessment were the most important weather variables in all ANN models. A set of weights from the ANN models was used to calculate the overall risk of anthracnose for the various sites. Sites with high and low anthracnose risk are present in both continents, and weather conditions at centres of diversity in Brazil and Colombia do not appear to be more conducive than conditions in Australia to serious anthracnose development. [source] Census and monitoring based on individually identifiable vocalizations: the role of neural networksANIMAL CONSERVATION, Issue 2 2002Andrew M. R. Terry Vocal individuality is widely suggested as a method for identifying individuals within a population. But few studies have explored its performance in real or simulated conservation situations. Here we simulated the use of vocal individuality to monitor the calling corncrake (Crex crex), a secretive and endangered land rail. Our data set contained 600 calls from 30 individuals and was used to simulate a population of corncrakes being counted and monitored. We tested three different neural network models for their ability to discriminate between and to identify individuals. Neural networks are non-linear classification tools widely applied to both biological and non-biological identification tasks. Backpropagation and probabilistic neural networks were used to simulate the reidentification of members of a known population (monitoring) and a Kohonen network was used to simulate the counting of a population of unknown size (census). We found that both backpropagation and probabilistic networks identified all individuals correctly all the time, irrespective of sample size. Kohonen networks were more variable in performance but estimated population size to within one individual of the actual size. Our results indicate that neural networks can be used effectively together with recordings of vocalizations in census and monitoring tasks. [source] FCCU simulation based on first principle and artificial neural network modelsASIA-PACIFIC JOURNAL OF CHEMICAL ENGINEERING, Issue 6 2009Maria Mihe Abstract A first principle model has been developed for the reactor,regenerator system based on construction and operating data from an industrial fluid catalytic cracking unit (FCCU). The first principle model takes into account the main FCCU subsystems: reactor riser, regenerator, stripper, catalyst circulation lines, air blower, wet gas compressor and main fractionator. A five-lump kinetic scheme has been considered for the reactions taking place in the reactor riser. Subsequently, an artificial neural network (ANN) model has been built for the complex FCCU system. The dynamic simulator, based on the previously developed first principle model, served as the source of reliable data for ANN design, training and testing. The ANN developed model was successfully trained and tested. Comparison between first principle and neural network based model leads to a very good match between the two models. Results show the substantial reduction of the computation time featured by the ANN model compared to the first principle model, demonstrating its potential use for real-time implementation in model-based control algorithms. Copyright © 2009 Curtin University of Technology and John Wiley & Sons, Ltd. [source] Neural Network Prediction of Biomass Digestibility Based on Structural FeaturesBIOTECHNOLOGY PROGRESS, Issue 2 2008Jonathan P. O'Dwyer Plots of biomass digestibility are linear with the natural logarithm of enzyme loading; the slope and intercept characterize biomass reactivity. The feed-forward back-propagation neural networks were performed to predict biomass digestibility by simulating the 1-, 6-, and 72-h slopes and intercepts of glucan, xylan, and total sugar hydrolyses of 147 poplar wood model samples with a variety of lignin contents, acetyl contents, and crystallinity indices. Regression analysis of the neural network models indicates that they performed satisfactorily. Increasing the dimensionality of the neural network input matrix allowed investigation of the influence glucan and xylan enzymatic hydrolyses have on each other. Glucan hydrolysis affected the last stage of xylan digestion, and xylan hydrolysis had no influence on glucan digestibility. This study has demonstrated that neural networks have good potential for predicting biomass digestibility over a wide range of enzyme loadings, thus providing the potential to design cost-effective pretreatment and saccharification processes. [source] Artificial Neural Networks and the Study of the Psychoactivity of Cannabinoid CompoundsCHEMICAL BIOLOGY & DRUG DESIGN, Issue 6 2010Káthia M. Honório Cannabinoid compounds have widely been employed because of its medicinal and psychotropic properties. These compounds are isolated from Cannabis sativa (or marijuana) and are used in several medical treatments, such as glaucoma, nausea associated to chemotherapy, pain and many other situations. More recently, its use as appetite stimulant has been indicated in patients with cachexia or AIDS. In this work, the influence of several molecular descriptors on the psychoactivity of 50 cannabinoid compounds is analyzed aiming one obtain a model able to predict the psychoactivity of new cannabinoids. For this purpose, initially, the selection of descriptors was carried out using the Fisher's weight, the correlation matrix among the calculated variables and principal component analysis. From these analyses, the following descriptors have been considered more relevant: ELUMO (energy of the lowest unoccupied molecular orbital), Log P (logarithm of the partition coefficient), VC4 (volume of the substituent at the C4 position) and LP1 (Lovasz,Pelikan index, a molecular branching index). To follow, two neural network models were used to construct a more adequate model for classifying new cannabinoid compounds. The first model employed was multi-layer perceptrons, with algorithm back-propagation, and the second model used was the Kohonen network. The results obtained from both networks were compared and showed that both techniques presented a high percentage of correctness to discriminate psychoactive and psychoinactive compounds. However, the Kohonen network was superior to multi-layer perceptrons. [source] Modeling of Methane Oxidative Coupling under Periodic Operation by Neural NetworkCHEMICAL ENGINEERING & TECHNOLOGY (CET), Issue 5 2005F. Abdolahi Abstract A set of feed forward multilayer neural network models have been proposed to predict CH4 conversion, C2 and ethylene selectivity of methane oxidative coupling under periodic operation. These parameters predicted by the proposed neural network are based on cycle period, cycle split, and CH4 and O2 mole fractions in the first and second part of the period. Due to the dynamic nature of periodic operation and the kinetic complexity of the investigated reactions, the proposed approach is an effective tool to model the system. The agreement between model predictions and experimental data was quite satisfactory. The models could be employed to optimize the experimental conditions in order to get better output from the catalytic reaction. It is concluded that the neural network is an effective tool for modeling catalytic chemical reactions under periodic operation. [source] Forecasting Daily Patient Volumes in the Emergency DepartmentACADEMIC EMERGENCY MEDICINE, Issue 2 2008Spencer S. Jones MStat Abstract Background:, Shifts in the supply of and demand for emergency department (ED) resources make the efficient allocation of ED resources increasingly important. Forecasting is a vital activity that guides decision-making in many areas of economic, industrial, and scientific planning, but has gained little traction in the health care industry. There are few studies that explore the use of forecasting methods to predict patient volumes in the ED. Objectives:, The goals of this study are to explore and evaluate the use of several statistical forecasting methods to predict daily ED patient volumes at three diverse hospital EDs and to compare the accuracy of these methods to the accuracy of a previously proposed forecasting method. Methods:, Daily patient arrivals at three hospital EDs were collected for the period January 1, 2005, through March 31, 2007. The authors evaluated the use of seasonal autoregressive integrated moving average, time series regression, exponential smoothing, and artificial neural network models to forecast daily patient volumes at each facility. Forecasts were made for horizons ranging from 1 to 30 days in advance. The forecast accuracy achieved by the various forecasting methods was compared to the forecast accuracy achieved when using a benchmark forecasting method already available in the emergency medicine literature. Results:, All time series methods considered in this analysis provided improved in-sample model goodness of fit. However, postsample analysis revealed that time series regression models that augment linear regression models by accounting for serial autocorrelation offered only small improvements in terms of postsample forecast accuracy, relative to multiple linear regression models, while seasonal autoregressive integrated moving average, exponential smoothing, and artificial neural network forecasting models did not provide consistently accurate forecasts of daily ED volumes. Conclusions:, This study confirms the widely held belief that daily demand for ED services is characterized by seasonal and weekly patterns. The authors compared several time series forecasting methods to a benchmark multiple linear regression model. The results suggest that the existing methodology proposed in the literature, multiple linear regression based on calendar variables, is a reasonable approach to forecasting daily patient volumes in the ED. However, the authors conclude that regression-based models that incorporate calendar variables, account for site-specific special-day effects, and allow for residual autocorrelation provide a more appropriate, informative, and consistently accurate approach to forecasting daily ED patient volumes. [source] | |||||||||||||||||||||||||