Downloads & Free Reading Options - Results

Determining operator cognitive or functional state is a critical component of adaptive aiding systems. To determine cognitive state, we must decide which measured features will assist in distinguishing different levels of mental activity. Psychophysiological signals were collected for two levels of cognitive workload from which 43 measures were derived. Three feature reduction methods were applied, and the results were used as inputs to an artificial neural network for training and classification. Average classification accuracies up to 89.7% were achieved and the number of input features required was reduced by up to 84 percent.

Context. Nanoflares are small impulsive bursts of energy that blend with and possibly make up much of the solar background emission. Determining their frequency and energy input is central to understanding the heating of the solar corona. One method is to extrapolate the energy frequency distribution of larger individually observed flares to lower energies. Only if the power law exponent is greater than 2, is it considered possible that nanoflares contribute significantly to the energy input. Aims. Time sequences of ultraviolet line radiances observed in the corona of an active region are modelled with the aim of determining the power law exponent of the nanoflare energy distribution. Methods. A simple nanoflare model based on three key parameters (the flare rate, the flare duration time, and the power law exponent of the flare energy frequency distribution) is used to simulate emission line radiances from the ions Fe XIX, Ca XIII, and Si iii, observed by SUMER in the corona of an active region as it rotates around the east limb of the Sun. Light curve pattern recognition by an Artificial Neural Network (ANN) scheme is used to determine the values. Results. The power law exponents, alpha 2.8, 2.8, and 2.6 for Fe XIX, Ca XIII, and Si iii respectively. Conclusions. The light curve simulations imply a power law exponent greater than the critical value of 2 for all ion species. This implies that if the energy of flare-like events is extrapolated to low energies, nanoflares could provide a significant contribution to the heating of active region coronae.

The U.S. Air Force has identified a need for rapid, accurate and reliable detection and classification of fires. To address this need, a proof- of-concept neural network-based, intelligent machine vision interface for the detection of flame signatures in the visible spectrum has been developed. The objective of the work conducted under this Phase I program has been to determine the feasibility of using machine vision techniques and neural network computation to detect and classify visible spectrum signatures of fire in the presence of complex background imagery. Standard fire detectors which rely on heat or smoke sensing devices tend to be slow and to react only after the fire reaches a significant level. Current electromagnetic sensing techniques have the desired speed but lack accuracy. The Phase I program approach to these problems used machine vision techniques to generate digitally filtered HSI (Hue, Saturation, Intensity)-formatted video data. Once filtered, these data were then presented to an artificial neural network for analysis.

Concrete deterioration standards containing various levels of microcracks were engineered by adding calcium sulfate to the concrete mixture and curing under moisture at 38 deg. C (100 deg. F). The level of the mircocracks was classified according to the speed of the ultrasonic pulse velocity (UPV) through the specimens using the American Society for Testing and Material (ASTM) C 597 (ASTM 1994c) test method and was found to vary uniformly from 1,737 to 4,877 m/sec (5,700 to 16,000 ft/sec). After receiving some preprocessing, 186 ultrasonic pulse echo (UPE) signals were used as input training examples for the artificial neural network (ANN) system. Target values for the ANN were the measured UPVs as determined form the ASTM C 597 test method. The correlation coefficient from a least squares fit was 98.6 percent. After training, the ANN was performance tested with 30 UPE signals that the model had not seen in training. A least squares fit demonstrated that the output velocities from the ANN correlated well with the measured (target) UPVs. The correlation coefficient was 84.8 percent. The system was able to rank all six specimens in the correct order of deterioration. This investigation demonstrates that the automated interpretation of UPE signals for continuous interfaces by the ANN is feasible.

This report surveys the topic of object detection in digital images. It outlines a standard method of analysis for the perception process. Several imaging and recognition issues are identified and explored through the human visual system as a model which is then used for constructing an artificial perception system. This leads to the study of self-organized artificial neural networks. The study includes the Kohonen feature map and several of its variations. The report will next focus on the application of these neural networks to object recognition tasks.

This article is from Sensors (Basel, Switzerland) , volume 12 . Abstract This paper presents a proposal for an Artificial Neural Network (ANN)-based architecture for completion and prediction of data retrieved by underwater sensors. Due to the specific conditions under which these sensors operate, it is not uncommon for them to fail, and maintenance operations are difficult and costly. Therefore, completion and prediction of the missing data can greatly improve the quality of the underwater datasets. A performance study using real data is presented to validate the approach, concluding that the proposed architecture is able to provide very low errors. The numbers show as well that the solution is especially suitable for cases where large portions of data are missing, while in situations where the missing values are isolated the improvement over other simple interpolation methods is limited.

The aim of this work is the use of modular artificial neural networks (ANN) for data mining (Data Mining) and forecasting of various processes in the field of ecology and environmental protection, as well as the comparison of the results of the proposed model with the results of other data analysis methods (the methods of mathematical modeling and mathematical statistics)

Aims. We present an innovative artificial neural network (ANN) architecture, called Generative ANN (GANN), that computes the forward model, that is it learns the function that relates the unknown outputs (stellar atmospheric parameters, in this case) to the given inputs (spectra). Such a model can be integrated in a Bayesian framework to estimate the posterior distribution of the outputs. Methods. The architecture of the GANN follows the same scheme as a normal ANN, but with the inputs and outputs inverted. We train the network with the set of atmospheric parameters (Teff, logg, [Fe/H] and [alpha/Fe]), obtaining the stellar spectra for such inputs. The residuals between the spectra in the grid and the estimated spectra are minimized using a validation dataset to keep solutions as general as possible. Results. The performance of both conventional ANNs and GANNs to estimate the stellar parameters as a function of the star brightness is presented and compared for different Galactic populations. GANNs provide significantly improved parameterizations for early and intermediate spectral types with rich and intermediate metallicities. The behaviour of both algorithms is very similar for our sample of late-type stars, obtaining residuals in the derivation of [Fe/H] and [alpha/Fe] below 0.1dex for stars with Gaia magnitude Grvs

Statistical data point to the fact that the vast majority of the world population, even after working for a lifetime, when they retire, do not have significant reserves of financial resources in order to guarantee a good quality of life in the elderly. Bearing in mind that the financial stock market offers a viable opportunity for lifelong capital expansion; Through this work, we sought to develop an innovative technique to allow a simple support based on mathematical models, for support decision making by common people, for buying or selling market stocks. This is because the techniques that support decision-making are relatively complex and not widely mastered by the majority of the Brazilian population. The algorithm was proposed to better perform this task. It was made by one corresponding Artificial Neural Network of the “Multi-Layer Perceptron” type with “Backpropagation”. Because this ANN is suitable for learning patterns of historical series, which are usually the object of study of stock price behavior by technical analysis methodologies, that are widely used by the market. Therefore, a comparative study was carried out between the results found using the proposed ANN methodology versus the results obtained from simple technical analysis versus single purchase and sale operations in a period of one year. It was found that the ANN model used guided the achievement of superior results for operations with all the Stocks tested, thus proving to be a promising way to solve problems of this nature; related to the identification of mathematical patterns of historical series of the behavior of stock prices on the São Paulo stock exchange.

Introduction One of the most important sources of the sugar production is sugarcane.Sugar is one of the eight human food sources (wheat, rice, corn, sugar, cattle, sorghum, millet and cassava). Also sugarcane is mainly used for livestock feed, electricity generation, fiber and fertilizer and in many countries sugarcane is a renewable source for the biofuel. The efficient use of inputs in agriculture lead to the sustainable production and help to reduce the fossil fuel consumption and greenhouse gases emission and save financial resources. Furthermore, detecting relationship between the energy consumption and the yield is necessary to approach the sustainable agriculture. It is generally accepted that many countries try to reduce their dependence to agricultural crop productions of other countries. The being Independent on agricultural productions lead to take more attention to modern methods and the objective of all these methods is increasing the performance with the efficient use of inputs or optimizing energy consumptions in agricultural systems. Energy modeling is a modern method for farm management that this model can predict yield with using the different amount of inputs. The objective of this study was to predict sugarcane production yield and (greenhouse gas) GHG emissions on the basis of energy inputs. Materials and Methods This study was carried out in Khouzestan province of Iran. Data were collected from 55 plant farms in Debel khazai Agro-Industry using face to face questionnaire method. In this study, the energy used in the sugarcane production has considered for the energy analysis without taking into account the environmental sources of the energy such as radiation, wind, rain, etc. Energy consumption in sugarcane production was calculated based on direct and indirect energy sources including human, diesel fuel, chemical fertilizers, pesticides, machinery, irrigation water, electricity and sugarcane stalk. Energy values were calculated by multiplying inputs and outputs per hectare by their coefficients of energy equivalents. Input energy in agricultural systems includes both direct and indirect energy and renewable and non-renewable forms. Direct energies include human labor, diesel fuel, water for irrigation and electricity and indirect energies consisted of machinery, seed (cultivation of sugarcane has been done with cutting of sugarcane instead of seed), chemical fertilizer. Renewable energies include machinery, sugarcane stalk, chemical fertilizer while non-renewable energy consisted of machinery, chemical fertilizer, electricity and diesel fuel. Energy values were calculated by multiplying inputs and outputs per hectare by their coefficients of energy equivalents. The amounts of GHG emissions from inputs in sugarcane production per hectare were calculated by CO 2 emissions coefficient of agricultural inputs. Energy modeling is an attractive subject for engineers and scientists who are concerned about the energy management. In the energy area, many different of models have been applied for modeling future energy. An artificial neural network (ANN) is an artificial intelligence that it can applied as a predictive tool for nonlinear multi parametric. Artificial neural network has been applied successfully in structural engineering modeling ANNs are inspired by biological neural networks. Results and Discussion The total energy used in the farm operations during the sugarcane production and the energy output was 1742883.769 and 111000 MJha_1, respectively. Electricity (52%) and chemical fertilizers (16%) were the most influential factors in the energy consumption. The electricity contribution was the highest due to the low efficiency of energy conversion in electric motors which were used for irrigation in the study area. In some areas, inefficient surface irrigation wastes a lot of water and energy (in forms of electricity). Another reason is that electricity energy equivalent for Iranian electricity production is higher than developed countries because Iran’s electricity grid is highly dependent on fossil fuels, so that 95% of the electrical energy in Iran is generated in thermal power plants using fossil fuels sources. In addition, the electricity transmission system is too old. GHG emissions data analysis indicated that the total GHG emissions was 415337.62 kg ha -1 (CO 2 eq) kgCO 2 eq ha -1 in which burning trash with the share of 62% had the highest GHG emission and followed by electricity (32%), respectively. The ANN model with 7-5-15-1 and 5-5-1 structure were the best model for predicting the sugarcane yield and GHG emissions, respectively. The coefficients of determination (R 2 ) of the best topology were 0.98 and 0.99 for the sugarcane yield and GHG emissions, respectively. The values of RMSE for sugarcane production and GHG emission were found to be 0.0037 and 4.52×10-6, respectively. Conclusion The statistical parameters of R2 and RMSE demonstrated that the proposed artificial neural networks results have best accuracy and can predict the yield and GHG emission. It is generally showed that artificial neural networks have good potential to predict the yield of the sugarcane production.

Introduction One of the most important sources of the sugar production is sugarcane.Sugar is one of the eight human food sources (wheat, rice, corn, sugar, cattle, sorghum, millet and cassava). Also sugarcane is mainly used for livestock feed, electricity generation, fiber and fertilizer and in many countries sugarcane is a renewable source for the biofuel. The efficient use of inputs in agriculture lead to the sustainable production and help to reduce the fossil fuel consumption and greenhouse gases emission and save financial resources. Furthermore, detecting relationship between the energy consumption and the yield is necessary to approach the sustainable agriculture. It is generally accepted that many countries try to reduce their dependence to agricultural crop productions of other countries. The being Independent on agricultural productions lead to take more attention to modern methods and the objective of all these methods is increasing the performance with the efficient use of inputs or optimizing energy consumptions in agricultural systems. Energy modeling is a modern method for farm management that this model can predict yield with using the different amount of inputs. The objective of this study was to predict sugarcane production yield and (greenhouse gas) GHG emissions on the basis of energy inputs. Materials and Methods This study was carried out in Khouzestan province of Iran. Data were collected from 55 plant farms in Debel khazai Agro-Industry using face to face questionnaire method. In this study, the energy used in the sugarcane production has considered for the energy analysis without taking into account the environmental sources of the energy such as radiation, wind, rain, etc. Energy consumption in sugarcane production was calculated based on direct and indirect energy sources including human, diesel fuel, chemical fertilizers, pesticides, machinery, irrigation water, electricity and sugarcane stalk. Energy values were calculated by multiplying inputs and outputs per hectare by their coefficients of energy equivalents. Input energy in agricultural systems includes both direct and indirect energy and renewable and non-renewable forms. Direct energies include human labor, diesel fuel, water for irrigation and electricity and indirect energies consisted of machinery, seed (cultivation of sugarcane has been done with cutting of sugarcane instead of seed), chemical fertilizer. Renewable energies include machinery, sugarcane stalk, chemical fertilizer while non-renewable energy consisted of machinery, chemical fertilizer, electricity and diesel fuel. Energy values were calculated by multiplying inputs and outputs per hectare by their coefficients of energy equivalents. The amounts of GHG emissions from inputs in sugarcane production per hectare were calculated by CO 2 emissions coefficient of agricultural inputs. Energy modeling is an attractive subject for engineers and scientists who are concerned about the energy management. In the energy area, many different of models have been applied for modeling future energy. An artificial neural network (ANN) is an artificial intelligence that it can applied as a predictive tool for nonlinear multi parametric. Artificial neural network has been applied successfully in structural engineering modeling ANNs are inspired by biological neural networks. Results and Discussion The total energy used in the farm operations during the sugarcane production and the energy output was 1742883.769 and 111000 MJha_1, respectively. Electricity (52%) and chemical fertilizers (16%) were the most influential factors in the energy consumption. The electricity contribution was the highest due to the low efficiency of energy conversion in electric motors which were used for irrigation in the study area. In some areas, inefficient surface irrigation wastes a lot of water and energy (in forms of electricity). Another reason is that electricity energy equivalent for Iranian electricity production is higher than developed countries because Iran’s electricity grid is highly dependent on fossil fuels, so that 95% of the electrical energy in Iran is generated in thermal power plants using fossil fuels sources. In addition, the electricity transmission system is too old. GHG emissions data analysis indicated that the total GHG emissions was 415337.62 kg ha -1 (CO 2 eq) kgCO 2 eq ha -1 in which burning trash with the share of 62% had the highest GHG emission and followed by electricity (32%), respectively. The ANN model with 7-5-15-1 and 5-5-1 structure were the best model for predicting the sugarcane yield and GHG emissions, respectively. The coefficients of determination (R 2 ) of the best topology were 0.98 and 0.99 for the sugarcane yield and GHG emissions, respectively. The values of RMSE for sugarcane production and GHG emission were found to be 0.0037 and 4.52×10-6, respectively. Conclusion The statistical parameters of R2 and RMSE demonstrated that the proposed artificial neural networks results have best accuracy and can predict the yield and GHG emission. It is generally showed that artificial neural networks have good potential to predict the yield of the sugarcane production.

The aim of this paper is a determination of the shear strength of fiber reinforced polymer reinforced concrete flexural members without stirrups. For this purpose, a neural network approach was used. The weights and biases of the considered network determined based on best values which were optimized from the particle swarm optimization algorithm (PSO). For training the model, a collection of 108 datasets which was published in literature was applied. Six inputs including the compressive strength of concrete, flexural FRP reinforcement ratio, modulus of elasticity for FRP, shear span-to-depth ratio, member web width and adequate member depth used for creating the model while the shear strength considered as the output. The best structure for the network was obtained by a network with one hidden layer and ten nodes. The results indicated that artificial neural networks based on particle swarm optimization algorithm could be able to predict the strength of the considered RC elements.

This paper reviews application of Artificial Neural Networks in Aircraft Maintenance, Repair and Overhaul (MRO). MRO solutions are designed to facilitate the authoring and delivery of maintenance and repair information to the line maintenance technicians who need to improve aircraft repair turn around time, optimize the efficiency and consistency of fleet maintenance and ensure regulatory compliance. The technical complexity of aircraft systems, especially in avionics, has increased to the point at which it poses a significant troubleshotting and repair challenge for MRO personnel. As per the existing scenario, the MRO systems in place are inefficient. In this paper, we propose the centralization and integration of the MRO database to increase its efficiency. Moreover the implementation of Artificial Neural Networks in this system can rid the system of many of its deficiencies. In order to make the system more efficient we propose to integrate all the modules so as to reduce the efficacy of repair.

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.

Recurrent and feedforward artificial neural networks are developed as wavefront reconstructors. The recurrent neural network studied is the Hopfield neural network and the feedforward neural network studied is the single layer perceptron artificial neural network. The recurrent artificial neural network input features are the wavefront sensor slope outputs and neighboring actuator feedback commands. The feedforward artificial neural network input features are just the wavefront sensor slope outputs. Both artificial neural networks use their inputs to calculate deformable mirror actuator commands. The effects of training are examined.

No abstract available

Improved estimates of near-surface air temperature and air humidity are critical to the development of more accurate turbulent surface heat fluxes over the ocean. Recent progress in retrieving these parameters has been made through the application of artificial neural networks (ANN) and the use of multi-sensor passive microwave observations. Details are provided on the development of an improved retrieval algorithm that applies the nonlinear statistical ANN methodology to a set of observations from the Advanced Microwave Scanning Radiometer (AMSR-E) and the Advanced Microwave Sounding Unit (AMSU-A) that are currently available from the NASA AQUA satellite platform. Statistical inversion techniques require an adequate training dataset to properly capture embedded physical relationships. The development of multiple training datasets containing only in-situ observations, only synthetic observations produced using the Community Radiative Transfer Model (CRTM), or a mixture of each is discussed. An intercomparison of results using each training dataset is provided to highlight the relative advantages and disadvantages of each methodology. Particular emphasis will be placed on the development of retrievals in cloudy versus clear-sky conditions. Near-surface air temperature and humidity retrievals using the multi-sensor ANN algorithms are compared to previous linear and non-linear retrieval schemes.

A method is developed to incorporate neural network model based upon the Backpropagation algorithm for material response into nonlinear elastic truss analysis using the initial stiffness method. Different network configurations are developed to assess the accuracy of neural network modeling of nonlinear material response. In addition to this, a scheme based upon linear interpolation for material data, is also implemented for comparison purposes. It is found that neural network approach can yield very accurate results if used with care. For the type of problems under consideration, it offers a viable alternative to other material modeling methods.

This dissertation research extends the current knowledge of feature saliency in artificial neural networks (ANN). Feature saliency measures allow for the user to rank order the features based upon the saliency, or relative importance, of the features. Selecting a parsimonious set of salient input features is crucial to the success of any ANN model. In this research, several methodologies were developed using the Signal to Noise Ratio (SNR) Feature Screening Method and its associated SNR Saliency Measure for selecting a parsimonious set of salient features to classify pilot workload in addition to air traffic controller workload. Candidate features were derived from electroencephalography (EEG), electrocardiography (EKG), electro-oculography (EOG), and respiratory gauges. In addition, a new saliency measure was developed that can account for time in Elman Recurrent Neural Networks (RNN). This Partial Derivative Based Spatial Temporal Saliency Measure is used via a Spatial Temporal Feature Screening Method for selecting a parsimonious set of salient features in both time and space. Finally, a technique for investigating the memory capacity of an Elman RNN was developed.

This paper examines how predictive modeling can be used to study application behavior. A relatively new technique, artificial neural networks (ANNs), was applied to help predict which students were likely to get into a large Research I university. Data were obtained from a university in Iowa. Two cohorts were used, each containing approximately 20,000 records. The results of the new techniques were compared to those from the traditional analysis tool, logistic regression modeling. ANNs have several advantages over traditional statistical methods. ANNs do not require knowledge of the functional relationship between the independent variables and the dependent variables to estimate the model. Unlike traditional statistical techniques, ANNs learn from examples with a small number of prior assumptions about structural relationships. Other advantages and disadvantages are discussed. The addition of artificial intelligence models is an exciting new area that may be used to explore the complex processes in educational institutions. (Contains 3 figures, 7 tables, and 48 references.) (SLD)

The simulation of runoff from a Himalayan Glacier basin using an Artificial Neural Network (ANN) is presented. The performance of the ANN model is found to be superior to the Energy Balance Model and the Multiple Regression model. The RMS Error is used as the figure of merit for judging the performance of the three models, and the RMS Error for the ANN model is the latest of the three models. The ANN is faster in learning and exhibits excellent system generalization characteristics.

Accurate wave prediction and supplement is an important task in determining constructions and management of coastal structures. However, determination of wave characteristics is of particular importance. In the present study, the artificial intelligence methodology of neural networks is used to forecast the waves based on learning the characteristics of observed waves, rather than the use of the wind information. The measurements from a single station at Bushehr, North coast of the Persian Gulf, for the period July 2007 - August 2007 were used to train and to validate the employed neural networks. The results obtained show the feasibility of the neural wave characteristics forecasts for 1 and 2 h in terms of the correlation coefficient (0.78–0.9), root mean square error (.03-.07) and scatter index (0.2–0.4). Therefore, the proposed methodology could be successfully used for site-specific forecasts. It is shown that the data produced with the approach developed in this work have statistical properties very close to the properties of the measurements, thus proving that this approach can be used as a reliable tool for wind wave forecasting in coastal areas, complementary to spectral and numerical wave models.

The paper develops important fundamental steps in applying artificial neural networks in the design of intelligent control systems. Different architectures including single layered and multi layered of neural networks are examined for controls applications. The importance of different learning algorithms for both linear and nonlinear neural networks is discussed. The problem of generalization of the neural networks in control systems together with some possible solutions are also included.

Artificial neural networks can provide improved computational efficiency relative to existing methods when an algorithmic description of functional relationships is either totally unavailable or is complex in nature. For complex calculations, significant reductions in elapsed computation time are possible. The primary goal is to demonstrate the applicability of artificial neural networks to composite material characterization. As a test case, a neural network was trained to accurately predict composite hygral, thermal, and mechanical properties when provided with basic information concerning the environment, constituent materials, and component ratios used in the creation of the composite. A brief introduction on neural networks is provided along with a description of the project itself.