Inputs Of Artificial Neural Network Research Articles

Short-term wind speed prediction at Bogdanci power plant in FYROM using an artificial neural network

ABSTRACTThe present study targets short-term wind speed prediction of the wind turbine station at Bogdanci in the Former Yugoslav Republic of Macedonia (FYROM), using artificial neural network (ANN) method. Wind directions and meteorological parameters (temperature, pressure, and humidity) measured at the interval of 10 min in between May 2015 and September 2015 have been used as the input of ANN to predict four kinds of wind speed (rotation mean, hub mean, tip low mean, and base mean). The best performance of ANN method was achieved using wind direction base mean (WDBM) in September 2015, and using temperature in May 2015. Reasonable performance of ANN method was achieved in the rest of the month.

ECONOMIC BENEFIT EVALUATION OF INDUSTRIAL ENTERPRISES BASED ON BP NEURAL NETWORK OPTIMIZATION ALGORITHM

The economic evaluation methods of existing industrial enterprises have many limitations. In this paper, an economic benefit evaluation method of industrial enterprises based on BP neural network optimization algorithm is proposed. This method takes the economic indicators of enterprises as input of artificial neural network, and uses the optimized BP neural network model to evaluate and analyze enterprises. The running time is greatly shortened, and the evaluation results are objective and accurate. An example is given to illustrate the implementation of the method. The example shows the feasibility of the method. In the fast-changing market situation, the sustainable development of enterprises has attracted the attention of all sectors of society and has become the focus of research. The sustainable development of the enterprise is the objective requirement of the sustainable development of the economy, the guarantee for the long-term economic benefit of the enterprise, and the fundamental method and way to realize the long-term development of the enterprise. Therefore, for enterprises, sustainable development is the primary task of enterprises. The research on sustainable development of enterprises has become a hot topic in the practice and theory field of enterprise management. However, there has been no effective and systematic theory on the index system, quantification and evaluation methods of the evaluation of the sustainable development of enterprises

Electricity Sales Forecasting Using Hybrid Autoregressive Integrated Moving Average and Soft Computing Approaches in the Absence of Explanatory Variables

Electricity is important because it is the most common energy source that we consume and depend on in our everyday lives. Consequently, the forecasting of electricity sales is essential. Typical forecasting approaches often generate electricity sales forecasts based on certain explanatory variables. However, these forecasting approaches are limited by the fact that future explanatory variables are unknown. To improve forecasting accuracy, recent hybrid forecasting approaches have developed different feature selection techniques (FSTs) to obtain fewer but more significant explanatory variables. However, these significant explanatory variables will still not be available in the future, despite being screened by effective FSTs. This study proposes the autoregressive integrated moving average (ARIMA) technique to serve as the FST for hybrid forecasting models. Aside from the ARIMA element, the proposed hybrid models also include artificial neural networks (ANN) and multivariate adaptive regression splines (MARS) because of their efficient and fast algorithms and effective forecasting performance. ARIMA can identify significant self-predictor variables that will be available in the future. The significant self-predictor variables obtained can then serve as the inputs for ANN and MARS models. These hybrid approaches have been seldom investigated on the electricity sales forecasting. This study proposes several forecasting models that do not require explanatory variables to forecast the industrial electricity, residential electricity, and commercial electricity sales in Taiwan. The experimental results reveal that the significant self-predictor variables obtained from ARIMA can improve the forecasting accuracy of ANN and MARS models.

A methodological approach for the development and verification of artificial neural networks based on an application to wave–structure interaction processes

ABSTRACTThis contribution presents a set of original and innovative methodological procedures for the development and the verification of artificial neural networks (ANNs). The procedures are conceived to provide a practical support in the build-up and verification processes of ANNs and address the following open issues: (i) the possibility to a-priori know the minimum size and the best assortment of the training database to optimize the ANN performance; (ii) the verification of the adequacy and effectiveness of the ANN input parameters, in order to avoid redundant information that may cause overfitting; and (iii) the assessment of the reliability of the ANN predictions when applied to new data. For this purpose, the procedures are applied to an existing ANN tool that the authors have recently designed for the prediction of the main parameters characterizing wave interaction with coastal and harbor structures. The main outcomes of the analyses suggest that (i) the size of training database depends on the ANN degrees of freedom; (ii) the use of three literature indicators allows to verify the appropriate selection of the input parameters; and (iii) the Euclidean distance among training data and new inputs can provide a useful a-priori indication of the reliability of the ANN predictions.

Comparison of DC link current and stator phase current in inverter switching faults detection of PMSM drives in HEVs

In this paper, a robust method for detection of inverter short circuit faults in field oriented control (FOC) of permanent magnet synchronous motor (PMSM) drive that is used frequently in hybrid electric vehicles (HEV) thanks to high power density and high efficiency is introduced. In the proposed method, a fault diagnostic and protection technique is developed by using discrete wavelet transform (DWT) and artificial neural network (ANN). The Symlet2 wavelet is selected to perform stator current analysis and the DWT coefficients of the motor currents are used as inputs of ANN for detecting inverter faults in PMSM drives. In HEVs, motor faults can cause permanent damage and accidents. So the early detection of PMSM drive faults in HEV will be provided by the proposed method. For implementing this method, the Matlab program is used to process DWT of signals. DC link and phase currents are compared in inverter switch faults detection and the results show that the proposed technique is very effective for fault diagnostic.

Intelligent performance evaluation of aquifer storage and recovery systems in freshwater aquifers

We present artificial neural network (ANN) based software for rapidly predicting the recovery effectiveness (REN) of aquifer storage and recovery (ASR) wells in fresh water aquifers. The REN performance criterion equals the amount of the water injected in an ASR well that is recoverable via the same well during a specified extraction period. The software circumvents the need to prepare and run computationally intensive simulations, by invoking ANN models as surrogate simulators. The paper presents the development of the ANN models and a graphical user interface (GUI) to facilitate using the ANN models and to perform sensitivity analysis. ANN inputs include all factors significantly affecting REN in freshwater aquifers. The software can evaluate REN in any ASR system in confined aquifers whose parameters are within the range of parameters used for training the ANNs in this study.

Using different classification models in wheat grading utilizing visual features

AbstractWheat is one of the most important strategic crops in Iran and in the world. The major component that distinguishes wheat from other grains is the gluten section. In Iran, sunn pest is one of the most important factors influencing the characteristics of wheat gluten and in removing it from a balanced state. The existence of bug-damaged grains in wheat will reduce the quality and price of the product. In addition, damaged grains reduce the enrichment of wheat and the quality of bread products. In this study, after preprocessing and segmentation of images, 25 features including 9 colour features, 10 morphological features, and 6 textual statistical features were extracted so as to classify healthy and bug-damaged wheat grains of Azar cultivar of four levels of moisture content (9, 11.5, 14 and 16.5% w.b.) and two lighting colours (yellow light, the composition of yellow and white lights). Using feature selection methods in the WEKA software and the CfsSubsetEval evaluator, 11 features were chosen as inputs of artificial neural network, decision tree and discriment analysis classifiers. The results showed that the decision tree with the J.48 algorithm had the highest classification accuracy of 90.20%. This was followed by artificial neural network classifier with the topology of 11-19-2 and discrimient analysis classifier at 87.46 and 81.81%, respectively

Forgiveness and trust dynamics on social networks

Social media users can easily be offended or hurt on those platforms, which leads to discomfort and health issues such as stress and anxiety. Forgiveness plays an important role to maintain healthy online relationships, which is the central constituent of social dynamics, from cooperation to social cohesion. While most prior studies have focused on analyzing forgiveness factors in offline settings using statistical methods, this study offers a new perspective using a two-staged approach whereby a research model was tested using structural equation modeling (SEM), and then the results were used as inputs for artificial neural network (ANN) and fuzzy logic (FL) models. An agent-based simulation was then performed to shed light on a possible use of the implemented models. Combining ANN and FL provided more accurate prediction results. In addition, simulation experiments call attention to the potential benefits of forgiveness in maintaining connectedness in a social network. The main purpose of this investigation was to evaluate the applicability of soft computing techniques on forgiveness prediction. Instead of relying on data mining techniques, we looked into questions that can improve our understanding of how society works in a digital age. In addition, this study provides an interesting example of a different and insightful way of doing computational social science that is useful to both researchers and practitioners.

A novel dual-molality densitometer for gauging in annular two phase flows using radial basis function

Abstract This study presents a novel method for determining the density of liquid phase in annular regime of two phase flows by utilizing dual modality densitometry technique and artificial neural network (ANN) model of radial basis function (RBF). The detection system is comprised of one 137Cs radioactive source, one 1 inch sodium iodide (NaI) scintillation detector for registering transmitted photons and one 1 inch NaI detector for registering scattered photons. An experimental setup was designed in order to provide the required data for testing and training the ANN. Registered counts in two detectors were utilized as the inputs of ANN and density of liquid phase was used as the output of ANN. The results show that the proposed approach could be successfully applied for predicting the density of liquid phase in annular regime of gas-liquid two phase flows. The liquid phase density was predicted with root mean square error (RMSE) of less than 0.0155 without a prior knowledge of the void fraction percentage in annular regime.

Novel Biological Based Method for Robot Navigation and Localization

The capability and reliability are crucial characteristics of mobile robots while navigating in complex environments. These robots are expected to perform many useful tasks which can improve the quality of life greatly. Robot localization and decision-making are the most important cognitive processes during navigation. However, most of these algorithms are not efficient and are challenging tasks while robots navigate through complex environments. In this paper, we propose a biologically inspired method for robot decision-making, based on rat’s brain signals. Rodents accurately and rapidly navigate in complex spaces by localizing themselves in reference to the surrounding environmental landmarks. Firstly, we analyzed the rats’ strategies while navigating in the complex Y-maze, and recorded local field potentials (LFPs), simultaneously. The recorded LFPs were processed and different features were extracted which were used as the input in the artificial neural network (ANN) to predict the rat’s decision-making in each junction. The ANN performance was tested in a real robot and good performance is achieved. The implementation of our method on a real robot, demonstrates its abilities to imitate the rat’s decision-making and integrate the internal states with external sensors, in order to perform reliable navigation in complex maze.

Prediction of rupture risk in anterior communicating artery aneurysms with a feed-forward artificial neural network.

Anterior communicating artery (ACOM) aneurysms are the most common intracranial aneurysms, and predicting their rupture risk is challenging. We aimed to predict this risk using a two-layer feed-forward artificial neural network (ANN). 594 ACOM aneurysms, 54 unruptured and 540 ruptured, were reviewed. A two-layer feed-forward ANN was designed for ACOM aneurysm rupture-risk analysis. To improve ANN efficiency, an adaptive synthetic (ADASYN) sampling approach was applied to generate more synthetic data for unruptured aneurysms. Seventeen parameters (13 morphological parameters of ACOM aneurysm measured from these patients' CT angiography (CTA) images, two demographic factors, and hypertension and smoking histories) were adopted as ANN input. Age, vessel size, aneurysm height, perpendicular height, aneurysm neck size, aspect ratio, size ratio, aneurysm angle, vessel angle, aneurysm projection, A1 segment configuration, aneurysm lobulations and hypertension were significantly different between the ruptured and unruptured groups. Areas under the ROC curve for training, validating, testing and overall data sets were 0.953, 0.937, 0.928 and 0.950, respectively. Overall prediction accuracy for raw 594 samples was 94.8 %. This ANN presents good performance and offers a valuable tool for prediction of rupture risk in ACOM aneurysms, which may facilitate management of unruptured ACOM aneurysms. • A feed-forward ANN was designed for the prediction of rupture risk in ACOM aneurysms. • Two demographic parameters, 13 morphological aneurysm parameters, and hypertension/smoking history were acquired. • An ADASYN sampling approach was used to improve ANN quality. • Overall prediction accuracy of 94.8 % for the raw samples was achieved.

Neural Network-Based Formula for the Buckling Load Prediction of I-Section Cellular Steel Beams

Cellular beams are an attractive option for the steel construction industry due to their versatility in terms of strength, size, and weight. Further benefits are the integration of services thereby reducing ceiling-to-floor depth (thus, building’s height), which has a great economic impact. Moreover, the complex localised and global failures characterizing those members have led several scientists to focus their research on the development of more efficient design guidelines. This paper aims to propose an artificial neural network (ANN)-based formula to estimate the critical elastic buckling load of simply supported cellular beams under uniformly distributed vertical loads. The 3645-point dataset used in ANN design was obtained from an extensive parametric finite element analysis performed in ABAQUS. The independent variables adopted as ANN inputs are the following: beam’s length, opening diameter, web-post width, cross-section height, web thickness, flange width, flange thickness, and the distance between the last opening edge and the end support. The proposed model shows a strong potential as an effective design tool. The maximum and average relative errors among the 3645 data points were found to be 3.7% and 0.4%, respectively, whereas the average computing time per data point is smaller than a millisecond for any current personal computer.

Artificial Neural Network Based Target Recognition for Marine Search

<p>The key point of marine search and rescue is to find out and recognize the distress objects. At present, the visual search method is usually adopted to detect the ships in distress, and this method can only be used at good sea condition and visibility. In this paper, a new target detection and recognition system is proposed. The parameters of radar transmitter and echo graphics and the invariant moments of radar images are extracted as the system’s recognition features, and the system’s target classifier is based on Artificial Neural Networks (ANN). The developed recognition classifier has been tested using three kinds of target Images, the target’s features are used as the inputs of trained ANN and the outputs of networks are target classification. Sea experimental results show that the proposed method is well-clustering and with high classified accuracy.</p>

Combined application of neutron activation analysis using IECF device and neural network for prediction of cement elements

Gamma spectrum of a cement sample is not straightforward to analyze as a result of peak overlapping produced by Compton effect of gamma rays radiated from activated elements in the neutron activation process and also because of the change into the neutron energy spectrum in the target sample during activation. Artificial neural network (ANN) is an excellent solution for complex and nonlinear systems. Consequently, the use of ANN for quantitative analysis of major cement elements including Ca, Si, Al, and Fe would be very advantageous. Iranian inertial electrostatic confinement fusion device is a fast, monoenergetic and steady neutron generator. It was simulated as a high-energy neutron source for performing neutron activation analysis. In the present study, a library of 29 members of delayed gamma-ray spectra of knowing cement samples were generated via MCNPX version 2.7. Specific photo-peaks related to Ca, Si, Al and Fe obtained from these spectra were used as inputs for ANN (21 of them for training and 8 for testing). Then, using MLP architecture, an ANN model has been presented to model the system to predict the percentages of the elements in cement. The ANN model is optimized to have only a hidden layer with five neurons. The comparison between modeling data and results of proposed MLP network shows that there is a good consistency between them. The MAE of training set for Ca, Si and Fe outputs were 0.0351, 0.0656 and 0.0660, respectively, and the MAE of testing set for mentioned outputs were 0.0997, 0.3046 and 0.8699, respectively. Overall, it can be concluded that the defined dispensable errors show that this modeling is a good one as a prediction tool for the mentioned purpose.

Feature Selection and ANN Solar Power Prediction

A novel method of solar power forecasting for individuals and small businesses is developed in this paper based on machine learning, image processing, and acoustic classification techniques. Increases in the production of solar power at the consumer level require automated forecasting systems to minimize loss, cost, and environmental impact for homes and businesses that produce and consume power (prosumers). These new participants in the energy market, prosumers, require new artificial neural network (ANN) performance tuning techniques to create accurate ANN forecasts. Input masking, an ANN tuning technique developed for acoustic signal classification and image edge detection, is applied to prosumer solar data to improve prosumer forecast accuracy over traditional macrogrid ANN performance tuning techniques. ANN inputs tailor time-of-day masking based on error clustering in the time domain. Results show an improvement in prediction to target correlation, the R2 value, lowering inaccuracy of sample predictions by 14.4%, with corresponding drops in mean average error of 5.37% and root mean squared error of 6.83%.

Computer vision system for egg volume prediction using backpropagation neural network

Volume is one of considered aspects in egg sorting process. A rapid and accurate volume measurement method is needed to develop an egg sorting system. Computer vision system (CVS) provides a promising solution for volume measurement problem. Artificial neural network (ANN) has been used to predict the volume of egg in several CVSs. However, volume prediction from ANN could have less accuracy due to inappropriate input features or inappropriate ANN structure. This paper proposes a CVS for predicting the volume of egg using ANN. The CVS acquired an image of egg from top view and then processed the image to extract its 1D and 2 D size features. The features were used as input for ANN in predicting the volume of egg. The experiment results show that the proposed CSV can predict the volume of egg with a good accuracy and less computation time.

Computer vision system for egg volume prediction using backpropagation neural network

Volume is one of considered aspects in egg sorting process. A rapid and accurate volume measurement method is needed to develop an egg sorting system. Computer vision system (CVS) provides a promising solution for volume measurement problem. Artificial neural network (ANN) has been used to predict the volume of egg in several CVSs. However, volume prediction from ANN could have less accuracy due to inappropriate input features or inappropriate ANN structure. This paper proposes a CVS for predicting the volume of egg using ANN. The CVS acquired an image of egg from top view and then processed the image to extract its 1D and 2 D size features. The features were used as input for ANN in predicting the volume of egg. The experiment results show that the proposed CSV can predict the volume of egg with a good accuracy and less computation time.

Deep linear autoencoder and patch clustering-based unified one-dimensional coding of image and video

This paper proposes a unified one-dimensional (1-D) coding framework of image and video, which depends on deep learning neural network and image patch clustering. First, an improved K-means clustering algorithm for image patches is employed to obtain the compact inputs of deep artificial neural network. Second, for the purpose of best reconstructing original image patches, deep linear autoencoder (DLA), a linear version of the classical deep nonlinear autoencoder, is introduced to achieve the 1-D representation of image blocks. Under the circumstances of 1-D representation, DLA is capable of attaining zero reconstruction error, which is impossible for the classical nonlinear dimensionality reduction methods. Third, a unified 1-D coding infrastructure for image, intraframe, interframe, multiview video, three-dimensional (3-D) video, and multiview 3-D video is built by incorporating different categories of videos into the inputs of patch clustering algorithm. Finally, it is shown in the results of simulation experiments that the proposed methods can simultaneously gain higher compression ratio and peak signal-to-noise ratio than those of the state-of-the-art methods in the situation of low bitrate transmission.

Klasifikasi sinyal EMG berbasis jaringan syaraf tiruan dan discrete wavelet transform

Electromyograph signal (EMG) is a non-stationary biomedical signal, making it difficult to determine the pattern. The method normally used for signal analysis is Fast Fourier Transform (FFT), but it has some drawbacks because it requires stable signals. To answer this deficiency wavelet transformation is used, especially discrete wavelet transforms that can analyze the signal in both the realm of time and frequency. The method to be used in this research is wavelet transformation for signal analysis with decomposition up to level 7 using wavelet symlet 8. This feature extraction result is used as input of artificial neural network (ANN) type of propagation backward with architecture of 8 input layer, 5 hidden layer and 3 layers of output. ANN Turnback is able to recognize 3 types of EMG signals namely Normal, Myopathy and Neuropathy. Based on the feature extraction of EMG signal decomposition energy characteristics. Network architecture with 8 input layers. 5 hidden layers and 3 output layers Proven best in the introduction of EMG signals. The highest success rate is the introduction of EMop Myopathy signal pattern reaching 94%, so the network architecture is proposed to regenerate the EMG signal.

Simulation Study on the Effect of Reduced Inputs of Artificial Neural Networks on the Predictive Performance of the Solar Energy System

In recent years, there has been a strong growth in solar power generation industries. The need for highly efficient and optimised solar thermal energy systems, stand-alone or grid connected photovoltaic systems, has substantially increased. This requires the development of efficient and reliable performance prediction capabilities of solar heat and power production over the day. This contribution investigates the effect of the number of input variables on both the accuracy and the reliability of the artificial neural network (ANN) method for predicting the performance parameters of a solar energy system. This paper describes the ANN models and the optimisation process in detail for predicting performance. Comparison with experimental data from a solar energy system tested in Ottawa, Canada during two years under different weather conditions demonstrates the good prediction accuracy attainable with each of the models using reduced input variables. However, it is likely true that the degree of model accuracy would gradually decrease with reduced inputs. Overall, the results of this study demonstrate that the ANN technique is an effective approach for predicting the performance of highly non-linear energy systems. The suitability of the modelling approach using ANNs as a practical engineering tool in renewable energy system performance analysis and prediction is clearly demonstrated.