Accuracy Of Artificial Neural Network Research Articles

The Application of Artificial Neural Networks in Predicting Children’s Giftedness

Artificial neural networks have a wide use in the prediction and classification of different variables, but their application in the area of educational psychology is still relatively rare. The aim of this study was to examine the accuracy of artificial neural networks in predicting students’ general giftedness. The participants were 221 fourth grade students from one Croatian elementary school. The input variables for artificial neural networks were teachers’ and peers’ nominations, school grades, earlier school readiness assessment and parents’ education. The output variable was the result on the Standard Progressive Matrices (Raven, 1994), according to which students were classified as gifted or non-gifted. We tested two artificial neural networks’ algorithms: multilayer perceptron and radial basis function. Within each algorithm, a number of different types of activation functions were tested. 80% of the sample was used for training the network and the remaining 20% to test the network. For a criterion according to which students were classified as gifted if their result on the Standard Progressive Matrices was in the 95th centile or above, the best model was obtained by the hyperbolic tangent multilayer perceptron, which had a high accuracy of 100% of correctly classified non-gifted students and 75% correctly classified gifted students in the test sample. When the criterion was the 90th centile or above, the best model was also obtained by the hyperbolic tangent multilayer perceptron, but the accuracy was lower: 94.7% in the classification of non-gifted students and 66.7% in the classification of gifted students. The study has shown artificial neural networks’ potential in this area, which should be further explored. Keywords: gifted students, identification of gifted students, artificial neural networks

Spatial modeling of soil salinity using multiple linear regression, ordinary kriging and artificial neural network methods

ABSTRACTSalinity as an important property of soil plays a major role in reducing the fertility in the world. Accurate information about the spatial change of soil salinity is essential for sustainable soil management and utilization in agriculture lands. For this purpose, 150 soil samples were collected from Dashte-e-Tabriz Iran and tested and soil salinity was estimated by land surface parameters including elevation, aspect, length of slope, wetness index, slope and normalized difference vegetation index as basic parameters. In order to model and predict the salinity, ordinary kriging (OK), artificial neural networks (ANN) and multiple linear regressions (MLR) were used. Accuracy of models was evaluated by the coefficient of determination (R2), root mean square error (RMSE) and mean absolute error (MAE). Based on Pearson correlation, elevation, normalized difference vegetation and wetness indices were selected for soil salinity spatial modeling from six land surface parameters. The results showed that the ANN had the lowest RMSE and highest R2. The values of R2, RMSE and MAE were 0.36, 25.89 and 17.06 for regression and 0.56, 17.70 and 13.05 for OK and 0.69, 16.06 and 11.60 for ANN, respectively, which indicated more accuracy of ANN in comparison with MLR and OK.

Time series forecasting based on wavelet decomposition and feature extraction

Time series forecasting is one of the most important issues in numerous applications in real life. The objective of this study was to propose a hybrid neural network model based on wavelet transform (WT) and feature extraction for time series forecasting. The motivation of the proposed model, which is called PCA-WCCNN, is to establish a single simplified model with shorter training time and satisfactory forecasting performance. This model combines the principal component analysis (PCA) and WT with artificial neural networks (ANNs). Given a forecasting sequence, order of the original forecasting model is determined firstly. Secondly, the original time series is decomposed into approximation and detail components by employing WT technique. Then, instead of using all the components as inputs, feature inputs are extracted from all the sub-series obtained from the above step. Finally, based on the extracted features and all the sub-series, a famous neural network construction method called cascade-correlation algorithm is applied to train neural network model to learn the dynamics. As an illustration, the proposed model is compared with two classical models and two hybrid models, respectively. They are the traditional cascade-correlation neural network, back-propagation neural network, wavelet-based cascade-correlation network using all the wavelet components as inputs to establish one model (WCCNN) and wavelet-based cascade-correlation network with combination of each sub-series model (WCCNN multi-models). Results obtained from this study indicate that the proposed method improves the accuracy of ANN and can yield better efficiency than other four neural network models.

Severity Prediction of Traffic Accident Using an Artificial Neural Network

AbstractIn this paper, an artificial neural network (ANN) was used to predict the injury severity of traffic accidents based on 5973 traffic accident records occurred in Abu Dhabi over a 6‐year period (from 2008 to 2013). For each accident record, 48 different attributes had been collected at the time of the accident. After data preprocessing, the data were reduced to 16 attributes and four injury severity classes. In this study, WEKA (Waikato Environment for Knowledge Analysis) data‐mining software was used to build the ANN classifier. The traffic accident data were used to build two classifiers in two different ways. The whole data set were used for training and validating the first classifier (training set), while 90% of the data were used for training the second classifier and the remaining 10% were used for testing it (testing set). The experimental results revealed that the developed ANN classifiers can predict accident severity with reasonable accuracy. The overall model prediction performance for the training and testing data were 81.6% and 74.6%, respectively. To improve the prediction accuracy of the ANN classifier, traffic accident data were split into three clusters using a k‐means algorithm. The results after clustering revealed significant improvement in the prediction accuracy of the ANN classifier, especially for the training dataset. In this work, and in order to validate the performance of the ANN model, an ordered probit model was also used as a comparative benchmark. The dependent variable (i.e. degree of injury) was transformed from ordinal to numerical (1, 2, 3, 4) for (minor, moderate, sever, death). The R tool was used to perform an ordered probit. For each accident, the ordered probit model showed how likely this accident would result in each class (minor, moderate, severe, death). The accuracy of 59.5% obtained from the ordered probit model was clearly less than the ANN accuracy value of 74.6%. Copyright © 2016 John Wiley & Sons, Ltd.

Using pedotransfer functions to estimate soil hydraulic conductivity in the Loess Plateau of China

Soil hydraulic conductivity (Ks) is a crucial soil physical property that not only influences soil hydrological processes, but also the planning for vegetation recovery, irrigation practice and drainage design. However, Ks data are often lacking at large-scale soil database due to difficulties in direct measurement that is often labour intensive, time consuming and cost inefficient. The objective of this study was to compare the performance of different emerging methods [Multiple linear regression (MLR) and artificial neural network (ANN)] of Ks prediction. The pedotransfer function (PTF) is one such method that is based on selected factors closely correlated with Ks at regional scale. We collected disturbed and undisturbed soil samples in the 0–40cm soil layer at 243 sites across the entire typical Loess Plateau of China (430,000km2) and then measured Ks and the potentially related factors. The results showed that Ks was normally distributed with moderate a spatial variation (CV=67%). Correlation analysis indicated that bulk density (BD), saturated soil water content (SSWC), clay content (Clay), silt content (Silt) and latitude were closely correlated (p<0.05) with Ks. Although the accuracies of MLR and ANN were equal in terms of estimating Ks, the stability of PTF developed via ANN was not as good as that of MLR. Thus PTF developed via MLR, which included BD, Silt and Clay, was considered as the best model for estimating Ks. There is a need to closely monitor the stability and repeatability of PTF during comparison and determination of PTF.

A method to improve the stability and accuracy of ANN- and SVM-based time series models for long-term groundwater level predictions

The prediction of long-term groundwater level fluctuations is necessary to effectively manage groundwater resources and to assess the effects of changes in rainfall patterns on groundwater resources. In the present study, a weighted error function approach was utilised to improve the performance of artificial neural network (ANN)- and support vector machine (SVM)-based recursive prediction models for the long-term prediction of groundwater levels in response to rainfall. The developed time series models were applied to groundwater level data from 5 groundwater-monitoring stations in South Korea. The results demonstrated that the weighted error function approach can improve the stability and accuracy of recursive prediction models, especially for ANN models. The comparison of the model performance showed that the recursive prediction performance of the SVM was superior to the performance of the ANN in this case study.

Application Of Fuzzy Regression Model For Real Estate Price Prediction

Many studies have been conducted for modeling the underlying non-linear relationship between pricing attributes and price of property to forecast the housing sales prices. In recent years, more advanced non-linear modeling techniques such as Artificial Neural Networks (ANN) and Fuzzy Inference Systems (FIS) have emerged as effective techniques to predict the house prices. In this paper, we propose a fuzzy least-squares regression-based (FLSR) model to predict the prices of real estates. A comprehensive comparison studies in terms of prediction accuracy and computational complexity of ANN, Adaptive Neuro Fuzzy Inference System (ANFIS) and FLSR has been carried out. ANN has been widely used to forecast the price of real estates for many years while ANFIS has been introduced recently. On the other hand, FLSR is comparatively new. To the best of our knowledge, no property prices prediction using FLSR was developed until recently. Besides, a detailed comparative evaluation on the performance of FLSR with other modeling approaches on property price prediction could not be found in the existing literature. Simulation results show that FLSR provides a superior prediction function as compared to ANN and FIS in capturing the functional relationship between dependent and independent real estate variables and has the lowest computational complexity.

Fire Risk Assessment Using Neural Network and Logistic Regression

Forest fire is one of the most important sources of land degradation that lead to deforestation and desertification processes. The presented work describes a methodology that employs logistic regression and artificial neural networks (ANN) to model forest fire risk and to recognize high potential area for fire occurrence. Different satellite and field data have been used in this work to model fire risk. These data include 12 static and dynamic parameters that are effective in fire occurrence and also 2001 to 2004 data was used to create model and data of year 2005 was used to evaluate created model. Two forest fire risk prediction models were created based on logistic regression and neural network in this research and both of them evaluated and compared. The result shows that neural network model is more accurate in fire point classification while logistic regression is sensitive to samples of fire points. To get high accuracy in logistic regression, it is necessary to be equilibrium the proportion of both fire and non-fire samples. Also different neural network structure was tested and the best architecture is a neural network with two hidden layer with 20, 28 neurons and logarithmic-sigmoid transfer function in both hidden layers. Accuracy of logistic regression and ANN in prediction of year 2005 fire was obtained 65.76 and 93.49, respectively.

Application of wavelet-artificial intelligence hybrid models for water quality prediction: a case study in Aji-Chay River, Iran

The accuracy of Artificial Neural Network (ANN), Adaptive Neuro-Fuzzy Inference System (ANFIS), wavelet-ANN and wavelet-ANFIS in predicting monthly water salinity levels of northwest Iran’s Aji-Chay River was assessed. The models were calibrated, validated and tested using different subsets of monthly records (October 1983 to September 2011) of individual solute (Ca2+, Mg2+, Na+, SO4 2− and Cl−) concentrations (input parameters, meq L−1), and electrical conductivity-based salinity levels (output parameter, µS cm−1), collected by the East Azarbaijan regional water authority. Based on the statistical criteria of coefficient of determination (R2), normalized root mean square error (NRMSE), Nash–Sutcliffe efficiency coefficient (NSC) and threshold statistics (TS) the ANFIS model was found to outperform the ANN model. To develop coupled wavelet-AI models, the original observed data series was decomposed into sub-time series using Daubechies, Symlet or Haar mother wavelets of different lengths (order), each implemented at three levels. To predict salinity input parameter series were used as input variables in different wavelet order/level-AI model combinations. Hybrid wavelet-ANFIS (R2 = 0.9967, NRMSE = 2.9 × 10−5 and NSC = 0.9951) and wavelet-ANN (R2 = 0.996, NRMSE = 3.77 × 10−5 and NSC = 0.9946) models implementing the db4 mother wavelet decomposition outperformed the ANFIS (R2 = 0.9954, NRMSE = 3.77 × 10−5 and NSC = 0.9914) and ANN (R2 = 0.9936, NRMSE = 3.99 × 10−5 and NSC = 0.9903) models.

Response surface methodology and artificial neural network modelling of an aqueous two-phase system for purification of a recombinant alkaline active xylanase

A two-stage polyethylene glycol (PEG)-phosphate aqueous two-phase system was used for purification of a highly thermostable and alkaline active recombinant xylanase. Response surface methodology (RSM) and artificial neural network (ANN) have been used to develop predictive models for simulation and optimization of purification process. Effects of pH, PEG molecular weight, concentrations of phosphate, PEG and NaCl on the partitioning of the target enzyme and the contaminants were studied using a central composite design of experiments. The best first stage purification was achieved using 6% PEG 6000, 20% phosphate and pH 6. The optimum back extraction stage system consist of 10% phosphate, 10% NaCl, pH 10 and the first stage separation top phase. After the two stage phase separations, about 78% of the original enzyme activity was recovered and the specific activity of the purified enzyme was increased by a factor of 6.7. Also, the aqueous two-phase system was scaled-up 100 times. After back-extraction, the specific activity increased 6.56 times with 72% total yield. A similar design was also used to obtain a training set for ANN. A comparison between the model results and experimental data gave high correlation coefficient (R2) and showed that both models were able to predict the partitioning behavior. The results demonstrated a higher prediction accuracy of ANN compared to RSM. This superiority of ANN over other multi factorial approaches could make this estimation technique a very helpful tool for purification process.

The Influence of Input Data Standardization Method on Prediction Accuracy of Artificial Neural Networks

Achieving good results in applying artificial neural networks (ANN) in predicting requires some preparatory works on the set of data. One of them is standardization which is necessary when nonlinear activation function is applied. Basing on predicting completion period of building contracts by multi-layer ANN with error backpropagation algorithm, six different methods of input data standardization were checked in order to determine which allows to achieve the most accurate predictions.

River Stage Forecasting Using Wavelet Packet Decomposition and Data-driven Models

This study develops and applies hybrid models combining wavelet packet decomposition and data-driven models for forecasting river stage and investigating their accuracy. The hybrid models are wavelet packet-based artificial neural network (WPANN) and wavelet packet-based adaptive neuro-fuzzy inference system (WPANFIS). Wavelet packet decomposition splits an input time series into approximation and detail components, and the decomposed time series are used as inputs to artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) for WPANN and WPANFIS models, respectively. The forecasting performances of WPANN and WPANFIS models are compared with those of ANN and ANFIS models. Based on performance evaluation indexes and graphical comparison, the WPANN and WPANFIS models produce better performance than ANN and ANFIS models in terms of model efficiency, and WPANFIS-coif18 model is also found to yield the best performance among all other models. Therefore, wavelet packet decomposition improves the accuracy of ANN and ANFIS models for forecasting river stage. The results indicate that river stage forecasting models combining wavelet packet decomposition and data-driven models can be used as an effective tool for forecasting river stage accuracy.

A New Artificial Neural Network Approach in Solving Inverse Kinematics of Robotic Arm (Denso VP6242).

This paper presents a novel inverse kinematics solution for robotic arm based on artificial neural network (ANN) architecture. The motion of robotic arm is controlled by the kinematics of ANN. A new artificial neural network approach for inverse kinematics is proposed. The novelty of the proposed ANN is the inclusion of the feedback of current joint angles configuration of robotic arm as well as the desired position and orientation in the input pattern of neural network, while the traditional ANN has only the desired position and orientation of the end effector in the input pattern of neural network. In this paper, a six DOF Denso robotic arm with a gripper is controlled by ANN. The comprehensive experimental results proved the applicability and the efficiency of the proposed approach in robotic motion control. The inclusion of current configuration of joint angles in ANN significantly increased the accuracy of ANN estimation of the joint angles output. The new controller design has advantages over the existing techniques for minimizing the position error in unconventional tasks and increasing the accuracy of ANN in estimation of robot's joint angles.

Hybrid Fuzzy Jordan Network for Robust and Efficient Intrusion Detection System

Objective: The main objective of this paper is to improve the intrusion detection accuracy of neural networks by hybridized with Jordan network, applying novel Lyapunov function and changing input values as fuzzy values using fuzzy logic. Methods: In this research, the intrusion detection of NSL KDD dataset is carry out by neural network first . The performance of neural networks mainly depends on the parameters like number of hidden layer, no of node in the hidden layer and the no of epoch. Selecting the proper parameters values and weight initialization are the main difficulty in neural network. To overcome this issue a hybrid network by combining neural network with Jordan network is proposed which is highly sensitive to weight convergence. In hybrid network Lyapunov function is used to achieve the stability of equilibrium between two networks. But in this work a novel Lyapunov function is proposed to achieve global robust stability in hybrid network. A novel Lyapunov function uses a class of general activation functions which are not to be differentiable, bounded or monotonically nondecreasing. A set of criteria are derived to guarantee the existence, uniqueness and global robust stability of the equilibrium of hybrid networks with time delays. Then the learning ability of hybrid network is improved by using fuzzy logic. The hybrid network improved by a novel Lyapunov and fuzzy logic is called as Improved Fuzzy Hybrid Jordan network and Artificial Neural Network (IHFJANN). Findings: Artificial Neural Network (ANN), Hybrid Jordan network and Artificial Neural Network (HJANN) and Improved Hybrid Fuzzy Jordan network and Artificial Neural Network (IHFJ ANN) are applied on NSL KDD training dataset to lean the type of available attacks. NSL training dataset contains 2500 instances and 38 attributes where as testing dataset contains 995 instances and 38 attributes. The learned model of three classifiers is used to predict the classes in test dataset. The performance measures are evaluated in terms of accuracy, precision, recall and f-measure values. Improvement: The classification accuracy of Artificial Neural Network (ANN), Hybrid Jordan network and Artificial Neural Network (HJANN) and Improved Hybrid Fuzzy Jordan network and Artificial Neural Network (IHFJANN) are 72%, 80% and 84% respectively. Accuracy is increased by 12% in IHFJANN than the ANN and 4% than the HJANN. The precision value of ANN, HJANN and IHFJANN are 0.46, 0.54 and 0.57 respectively. Precision value is increased by 0.9 in IHFJANN than the ANN and 0.3 than the HJANN. The recall value of ANN, HJANN and IHFJANN are 0.73, 0.81 and 0.84 respectively. Recall value is increased by 0.9 in IHFJANN than the ANN and 0.3 than the HJANN. The F-measure value of ANN, HJANN and IHFJANN are 0.58, 0.65 and 0.68 respectively. F-measure value is increased by 0.10 in IHFJANN than the ANN and 0.3 than the HJANN. The results proved that the proposed IHFJANN provides better performance than ANN and HJANN.

Dynamic modeling and optimization of cyanobacterial C-phycocyanin production process by artificial neural network

Artificial neural networks have been widely applied in bioprocess simulation and control due to their advantageous properties. However, their feasibility in long-term photo-production process modeling and prediction as well as their efficiency on process optimization have not been well studied so far. In the current study, an artificial neural network was constructed to simulate a 15-day fed-batch process for cyanobacterial C-phycocyanin production, which to the best of our knowledge has never been conducted. To guarantee the accuracy of artificial neural network, two strategies were implemented. The first strategy is to generate artificial data sets by adding random noise to the original data set, and the second is to choose the change of state variables as training data output. In addition, the first strategy showed the distinctive advantage of reducing the experimental effort in generating training data. By comparing with current experimental results, it is concluded that both strategies give the network great modeling and predictive power to estimate the entire fed-batch process performance, even when few original experimental data are supplied. Furthermore, by optimizing the operating conditions of a 12-day fed-batch process, a significant increase of 85.6% on C-phycocyanin production was achieved compared to previous work, which suggests the high efficiency of artificial neural network on process optimization.

Global location of mobile robots using Artificial Neural Networks in omnidirectional images

This paper presents a comparison of Mobile Robots localization methods through Artifical Neural Networks in omnidirectional images. After an overview about Mobile Robotics, this work focuses on omnidirectional vision. The motivation for this work is the implementation and comparison of feature extraction techniques that can be used in omnidirectional images seeking invariance to rotation and building descriptors that can be used in Neural Networks. Five feature extraction techniques with their adaptations for omnidirectional image were presented and compared. The results were shown in order to choose the most suitable feature extractor for this application. The feature extractorsare evaluated with respect to time processing and quality of scene description (accuracy of Artificial Neural Network) The results are satisfactory and elect GIST descriptor as the most suitable for the application.

Performance evaluation of hybrid Wavelet-ANN and Wavelet-ANFIS models for estimating evapotranspiration in arid regions of India

This paper evaluates the ability of wavelet transform in improving the accuracy of artificial neural network (ANN) and adaptive neuro-fuzzy interface systems (ANFIS) models. In this study, the performance of hybrid Wavelet-ANN and Wavelet-ANFIS models for estimating daily evapotranspiration in arid regions was evaluated. Prior to the development of models, gamma test was used to identify the best input combinations that could be used under limited data scenario. Performance of the proposed hybrid models was compared to ANN, ANFIS, and conventionally used Hargreaves equation. The results revealed that use of wavelet transform as data preprocessing technique enhanced the efficiency of ANN and ANFIS models. Wavelet-ANN and Wavelet-ANFIS performed reasonably better than other models. Better handling of wavelet-decomposed input variables enabled Wavelet-ANN models to perform slightly better than the Wavelet-ANFIS models. W-ANN2 (RMSE = 0.632 mm/day and R = 0.96) was found to be the best model for estimating daily evapotranspiration in arid regions. The proposed W-ANN2 model used second-level db3 wavelet-decomposed subseries of temperature and previous day evapotranspiration values as inputs. The study concludes that hybrid Wavelet-ANN and Wavelet-ANFIS models can be effectively used for modeling evapotranspiration.

English

We investigated the effect of the 2007 to 2008 Brazilian financial crisis on nonlinearity and the prediction accuracy of artificial neural networks on monthly soybean prices in Brazil. To determine the exogenous variable, the commodity’s logarithm return was calculated. The best period for the series simulation was then identified, simulations carried out and the model validated. Model forecasting results were satisfactory for all samples. A group method of data handling (GMDH) methodology was capable of demonstrating the returns’ non-randomness, denoting marketing inefficiency, arbitrage opportunities and abnormal return to investors, especially after the financial crisis of 2007 to 2008. Key words: Financial crisis, predictability, nonlinearity, soybean.

English

The study investigates the accuracy of bagging ensemble models (i.e., bagged artificial neural networks (BANN) and bagged regression trees (BRT)) in monthly crude oil price forecasting. Two ensemble models are obtained by coupling bagging and two simple machine learning models (i.e., artificial neural networks (ANN) and classification and regression trees (CART)) and results are compared with those of the single ANN and CART models. Analytical results suggest that ANN based models (ANN & BANN) are superior to tree-based models (RT & BRT) and the bagging ensemble method could optimize the forecast accuracy of the both single ANN and CART models in monthly crude oil price forecasting. Key words: Artificial neural networks, bagging (bootstrap aggregating), classification and regression trees, ensemble models, forecasting.

Forecasting Groundwater Level by Artificial Neural Networks as an Alternative Approach to Groundwater Modeling

Abstract The main purpose of this article is to apply feed forward back propagation neural network (FNN) to predict groundwater level of Aghili plain, which is located in southwestern Iran. An optimal design is completed for the two hidden layers with four different algorithms: descent with momentum (GDM), Levenberg Marquardt (LM), resilient back propagation (RP), and scaled conjugate gradient (SCG). The training data for ANN is obtained from observation data. Rain, evaporation, relative humidity, temperature, discharge of irrigation canal, and groundwater recharge from the plain boundary were used in input layer while future groundwater level was used as output layer. Before training, the available data were divided into three groups, according to hydrogeological characteristics of different parts of the plain surrounding each piezometer. Statistical analysis in terms of Mean-Square-Error (MSE) and correlation coefficient (R) was used to investigate the prediction performance of ANN. FFN-LM algorithm has shown best result in the present study for all three hydrogeological groups. Now, to predict water level, the t time data (October 2003 to July 2009) and t+1 time data (October 2004 to July 2010) were used as input and output respectively. The best condition of this network was achieved for each group of data. Next, with defining the new input data related to August 2010 to January 2011 groundwater level was predicted for the following year. The achieved results of ANN model in contrast with results of finite difference model showed very high accuracy of artificial neural network in predicting groundwater level.