Artificial Neural Network (ANN)

Computing Information Systems Development Informatics and Allied Research Journal, 2013

In this paper, Artificial Neural Networks (ANN) and Regression Analysis models were considered to determine which of them performs better. Prediction was done using one hidden layer and three processing elements in the ANN model. Furthermore, prediction was done using regression analysis. The parameters of regression model were estimated using Least Square method. To determine the better prediction, mean square errors (MSE) attached to ANN and regression models were used. Seven real series were fitted and predicted with in both models. It was found out that the mean square error attached to ANN model was smaller than regression model which made ANN a better model in prediction.

Sistemas & Gestão

Many types of physical models have been developed for runoff estimation with successful results. However, accurate runoff estimation remains a challenging problem owing to the lack of field data and the complexity of its hydrological process. In this paper, a machine learning method for runoff estimation is presented as an alternative approach to the physical model. Various types of input variables and Artificial Neural Network (ANN) architectures were examined in this study. Results showed that a two-layer network with the tansig activation function and the Levenberg–Marquardt learning algorithm had the best performance. For this architecture, the most effective input vector consists of a catchment perimeter, canal length, slope, runoff coefficient, and rainfall intensity. However, results of multivariate analysis of variance indicated the significant interaction effect of input data and the ANN architecture. Thus, to create a suitable ANN model for runoff estimation, a systematic ...

International Journal of Electrical and Computer Engineering (IJECE)

Multiple linear regressions are an important tool used to find the relationship between a set of variables used in various scientific experiments. In this article we are going to introduce a simple method of solving a multiple rectilinear regressions (MLR) problem that uses an artificial neural network to find the accurate and expected output from MLR problem. Different artificial neural network (ANN) types with different architecture will be tested, the error between the target outputs and the calculated ANN outputs will be investigated. A recommendation of using a certain type of ANN based on the experimental results will be raised.

International Journal of Computer Aided Engineering and Technology, 2014

An Artificial Neural Network (ANN) is a mathematical model inspired by the biological behaviour of neurons and by the structure of the brain, which is used to solve a wide range of problems. A network is reached by connecting several neurons with a specific architecture (Hopfield Networks, Kohonen Networks, Perceptron, and so on), in which neurons learn through a process of self-organization. 1 During the learning process of the ANN, when a data is introduced into the network, just the neuron that has a positive activity inside the proximity will be activated at the exit stage. There is a wide variety of ANN models, which depend on the objective by which they were created, as well as the practical problem they solve. 3 During these last decades, several inconveniences about ANN applications have been found in the literature, 4,5,6,7 as the performance of the ANN neither have much relation to the amount of acquired information, nor the way the algorithm detects the information, 8 but also with issues like: the selection of the network model, the variables to incorporate on it and the pre-processing of the information that will form the training group. The ANN depends essentially on the exact information of the system under study, and the methods of training that must be used, as the algorithm of ANN during their training have the ability of identifying unnecessary data. 10 Besides, the routines of training require a huge amount of data to make sure that the results can be statistically precise 11 , but a lot of algorithms have been proposed to improve the performance of the ANN. 12, 13 Therefore, it can be seen that it is important to know more about the precision and the sturdiness of the ANN. 14 Given the wide range of applications of the ANN towards different areas of science (financial and economic modelling, market profiles -customer, medical applications, management of knowledge and discovering of data, optimization of industrial processes and quality control, among others) generate excellent results. Given the great versatility of the applications and the uses of the ANN, it is possible that can be used in system for which not necessarily has an optimum performance, they may be redundant or inefficient. So, that would be advisable assess the own characteristics of the nature of the problem to solve, in order to assess the application of an ANN.

International Journal of Data Science, 2021

Neural networks have been very important models across computer vision, natural language processing, speech and image recognition, aircraft safety and many more. It uses a variety of architectures that centres on the Multi-Layer Perceptron (MLP) which is the most commonly used type of Artificial Neural Network. MLP has been found to be good in terms of model precision in the usage of Homogenous Transfer/activation Functions (HTFs), especially with large data set. Based on the preliminary investigations of ranking of transfer functions by error variance (Udomboso, 2014), three HTFs are considered to perform better than other HTFs in prediction. These HTFs are the Hyperbolic Tangent Transfer functions (TANH), Hyperbolic Tangent Sigmoid Transfer function (TANSIG) and the Symmetric Saturating Linear Transfer Function (SSLTF). In this work, the performance of two Heterogeneous Transfer Functions (HETFs), which came as a result of the convolution of the three best HTFs, were compared with the performance of the three above listed HTFs. The hidden neurons used are 2, 5 and 10, while the sample sizes include 50, 100, 200, 500 and 1000. The data were divided into training sets of 90, 80 and 70 respectively. The results showed that the HETFs performed better in terms of the forecast using Mean Square Error (MSE), Mean Absolute Error (MAE) and Test Error as the forecast prediction criteria.

Journal of management and science, 2022

There are thousands of studies in the literature on the use of artificial neural network methods in estimation problems. As in all issues, modeling is one of the essential processes for the solution of estimation problems. In order to make a good prediction, it is necessary to pay attention to the necessary rules. The more attention is paid to the estimation stages, the more accurate the assessment will be, and the results can be generalized. In this study, publications in the literature on artificial neural networks were examined. This work aims to explore the studies on artificial neural networks and emphasize their importance. It is also of great importance to increase the number of studies in this field.

Biometrics & Biostatistics International Journal, 2015

Neural Networks are well known techniques for classification problems. They can also be applied to regression problems. For this, the R software packages neuralnet and RSNNS were utilized. Their application was tested with Fisher's iris dataset and a dataset from Draper and Smith and the results obtained from these models were studied.

2022 International Arab Conference on Information Technology (ACIT)

Traditional statistical models as tools for summarizing patterns and regularities in observed data can be used for making predictions. However, statistical prediction models contain small number of important predictors, which means limited informative capability. Also, predictive statistical models that provide some type of regular patterns that seems to hold true statistically, are used without previous understanding of causal mechanisms in the observed data. Machine learning methods like artificial neural networks as a special class of artificial intelligence provide the ability to interpret and understand data in more sophisticated way. NN methods use non-linear algorithms, considering links and associations between parameters, while statistical use linear processes to improve only short-term prediction's accuracy by minimizing cost function, often one-step-ahead, without considering medium and long-term ones. Disregarding that designing an optimal artificial neural network is very complex process, they are considered as potential solution for overcoming main flaws of statistical prediction models. However, they will not automatically improve predictions accuracy, so several artificial neural networks and traditional statistical methods are evaluated and analyzed through accuracy measures for prediction purposes in various fields of applications. Based on gained results, couple of techniques for improving artificial neural networks are proposed to get better accuracy results than statistical predictive methods.

2005

The Artificial Neural network is a functional imitation of simplified model of the biological neurons and their goal is to construct useful computers for real world problems. The ANN applications have increased dramatically in the last few years fired by both theoretical and practical applications in a wide variety of applications. A brief theory of ANN is presented and potential areas are identified and future trends are discussed.