Feedback Artificial Neural Network Research Articles

EFFECT OF LINEAR DATA PROCESSING PROCESSES ON THE PREDICTION PERFORMANCE OF THE NEURAL NETWORK: AN APPLICATION WITH EXCHANGE RATE DATA

This study investigated the effect of traditional data preprocessing processes on the prediction performance of predictions made with artificial neural network models. For this purpose, two different models were created and time series estimation was made. The original data was used in the first model, and in the second model, the data obtained by the traditional data preprocessing method in the time series were used. The data set consists of monthly real US Dollar/Turkish Lira rates between 2000M1 and 2022M2 for Turkey. Jordan model with feedback artificial neural network architecture is used for time series estimation. Estimation errors were calculated according to the Root Squared Value of Mean Squared Error (RMSE) criteria and the results were discussed according to this statistic. In the study, it was concluded that data processing reduces the estimation error of the nonlinear method.

Determination of Glaucoma Disease with Gray Level Co-occurrence Matrix Features

Glaucoma is a disease that causes an abnormal increase in intraocular pressure and therefore causes permanent damage to the optic nerves. Early and accurate diagnosis of the disease, known as the most "insidious" disease among eye diseases, is important. In this study, glaucoma prediction application was performed from high-resolution fundus photographs taken from an open-source database. Correlation, energy, homogeneity, contrast and entropy features were extracted from the segmented photographs using the gray-level co-occurrence matrix. Extracted features were divided into 66% test and 33% training after taking their average values. A 3-fold cross-validation was applied to the data and a feedback artificial neural network, classification and regression trees algorithm and k nearest neighbor algorithm were trained using 66% of the data. Classification success was also tested with 33% of test data. As a result, glaucoma and healthy individuals were classified with an average of 86.7% accuracy with the k nearest neighbor algorithm, an average of 87.8% accuracy with the decision trees, and an average of 96.7% accuracy with the artificial neural network algorithm. According to the results obtained, it was seen that glaucoma disease could be detected with high accuracy with the gray-level co-occurrence matrix features of glaucoma disease.

GREEN BONDS IN CLIMATE FINANCE AND FORECASTING OF CORPORATE GREEN BOND INDEX VALUE WITH ARTIFICIAL INTELLIGENCE

The effects of global climate change and increasing environmental awareness have led to an increase in the significance of climate projects and, accordingly, climate finance and green bonds. Despite the increasing significance, the fact that the price forecasting studies on green bonds are extremely scarce has been the main motivation of this study. The aim of this paper is to forecast the corporate green bond prices with the Artificial Neural Network model and to determine the predictor by addressing the conceptual framework of green bonds. For this purpose, the Multi-Layer Feedback Artificial Neural Network (MLF-ANN) model, in which S&P 500 index prices are determined as input and S&P green bond index prices as output, is designed. To determine whether the conventional bond prices are the predictor of the corporate green bonds, the S&P 500 index was used as the sole input of the forecasting model. The findings show that corporate green bond prices are forecasted with 1.13% Mean Absolute Percentage Error (MAPE) and 98.93% Regression Determination Coefficient (R2). The results of the research provide data to maximize profits and/or minimize risk for green bond investors and market makers, while providing insight into the effectiveness of green bonds in financing climate projects for policy makers. This paper is the first study in the literature in terms of proving the effectiveness of the MLF-ANN model in forecasting corporate green bonds and revealing that conventional bonds are predictor of green bonds. Thus, it is expected that the study will shed light on future studies.

Prediction of renewable energy consumption for future world by using artificial neural networks

Artificial intelligence has proven itself in many areas in combating complex and challenging problems. In this study, the estimation of the use of artificial neural networks in long term renewable energy consumption was undertaken. The study proposes an artificial intelligence predicting energy consumption and energy needs of houses and buildings in the future by using feedback artificial neural networks. In this study, "Google Project Sunroof-Solar Panel Power Consumption Offset Estimate" data set is used. With the database, artificial intelligence has been obtained by using artificial neural networks with feedback. The training of the artificial intelligence obtained was completed with 7999 samples with 25 different categories. This database, which Google collects, is obtained at high costs, so it is not possible for everyone to access such and its bases. Our artificial intelligence with feedback artificial neural network obtained a high percentage for training success. Validation success was high and test success was high too. Keywords: Artificial Neural Networks; Energy Consumption; Energy; Renewable Energy

Multi-step wind speed forecasting and Hurst analysis using novel hybrid secondary decomposition approach

Wind speed should be predicted in a sensitive and reliable manner for the effective use of wind energy in wind farms. However, the volatility and non-linearity features of wind make it difficult to do so. Hence, many researchers have focused on the development of reliable prediction models for wind speed. Aimed at this challenge, the present study proposes a hybrid model comprised of Ensemble Empirical Mode Decomposition Adaptive Noise (CEEMDAN), Local Mean Decomposition (LMD), Hurst and Back-propagation Neural Network (BPNN). This model is actualized as follows: First, wind speed time series is decomposed into its sub-components via CEEMDAN technique. The least irregular and unsystematic of the IMFs with the highest frequency obtained as a result of decomposition via CEEMDAN is subject to secondary decomposition using the LMD technique. The obtained components are subject to Hurst analysis to be transformed into micro, meso and macro scale series. These series are then applied on feedback artificial neural networks. The analysis results indicate that model proposed has a better performance than the compared traditional forecasting methods (EEMD-VDM-BPNN and EEMD-EWT-BPNN) with regard to prediction accuracy. The MAPE values obtained via the proposed hybrid model were observed to have decreased by 41.16% and 78.80% when compared with those obtained using traditional models.

Türkiye’de Aylık İşsizlik Oranlarının Yapay Sinir Ağları ile Öngörüsü

Since the labor market contains human factors, unlike other markets, the economic policies that are implemented to stabilize the labor market cannot be effective alone, therefore, social and psychological factors also come into play. As of today, it is seen that the high unemployment rates appear to be increasing every day and become one of the main issues of Turkey's economy. Unemployment becomes prevalent especially in the younger population of Turkey, and individuals in the young age group are rendered advantageous since the burden of subsistence does not devolve upon most of them. Upon considering that the pressure and adverse conditions caused by unemployment may be different for each age group and the economic and social policies that are required to be developed against such necessity to be different in this context, it is quite crucial to forecast the unemployment rate, especially for different age groups.The aim of the study is constituted by the forecasting of the monthly unemployment rates in Turkey depending on age groups via artificial neural networks. In line with this purpose, based on official data obtained from the TSI by taking into account the monthly unemployment rates for the age groups over the period 2005-2019 as well as the general unemployment rates for the same period, the monthly unemployment rates for the year 2019 were forecasted using feed-forward and feed-back artificial neural network models. As a result of the study, it was revealed with both error criteria and some visual findings that the observed values for all age groups, overall monthly unemployment rates, and the forecasting by artificial neural networks (ANN) were quite close to each other.

Dynamic prediction of gas wells based on feedback artificial neural network

Sudong gas wells vary hugely in production capacity, and meet extremely complex situation in dynamic changing. In view of Sudong gas wells with such characteristics, dynamic prediction of gas wells based on feedback artificial neural network is helpful to improve the exploitation productivity and management efficiency of the gas wells. In this paper, a prediction system based on feedback artificial neural network is developed, which can be used for analysis of dynamic changes of gas wells, forming gas well geological parameters and prediction model for production decline. The reliability, rationality and practicability of the prediction system are guaranteed through full verification and comparison of the predicted results.

Comparative study on logical analysis of data (LAD), artificial neural networks (ANN), and proportional hazards model (PHM) for maintenance prognostics

PurposeCondition-based maintenance (CBM) has become a central maintenance approach because it performs more efficient diagnoses and prognoses based on equipment health condition compared to time-based methods. CBM models greatly inform maintenance decisions. This research examines three CBM fault prognostics models: logical analysis of data (LAD), artificial neural networks (ANNs) and proportional hazard models (PHM). A methodology, which involves data pre-processing, formulating the models and analyzing model outputs, is developed to apply and compare these models. The methodology is applied on NASA’s Turbofan Engine Degradation data set and the structural health monitoring (SHM) data set from a Nova Scotia Bridge. Results are evaluated using three metrics: error, half-life error and a cost score. This paper concludes that the LAD and feedforward ANN models compares favorably to the PHM model. However, the feedback ANN does not compare favorably, and its predictions show much larger variance than the predictions from the other three methods. Based on these conclusions, the purpose of this paper is to provide recommendations on the appropriate situations in which to apply these three prognostics models.Design/methodology/approachLAD, ANNs and PHM methods are adopted to perform prognostics and to calculate the mean residual life (MRL) of eqipment using NASA’s Turbofan Engine Degradation data set and the SHM data set from a Nova Scotia Bridge. Statistical testing was used to evaluate the statistical differences between the approaches based on these metrics. By considering the differences in these metrics between the models, it was possible to draw conclusions about how the models perform in specific cases.FindingsResults were evaluated using three metrics: error, half-life error and a cost score. It was concluded that the LAD and feedforward ANN models compares favorably to the PHM model. However, the feedback ANN does not compare favorably and its predictions show much larger variance than the predictions from the other three methods. Overall the models predict failure after it has already occurred (negative error) when the residual life is large and vice versa.Practical implicationsIt was concluded that a good CBM prognostics model for practical implications can be determined based on three main considerations: accuracy, run time and data type. When accuracy is a main concern, as in the case where impacts of failure are large, LAD and feedforward neural network are preferred. The preference changes when run time is considered. If data can be easily collected and updating the model is performed often, the ANNs and LAD are preferred. On the other hand, if CM data are not easily obtainable and existing data are not representative of the population’s behavior, data type comes into play. In this case, PHM is preferred.Originality/valuePrevious research in the literature performed reviews of multiple independent studies on CBM techniques performed on different data sets. They concluded that it is typically harder to implement artificial intelligence models, because of difficulties in data procurement, but these approaches offer improved performance as compared to more traditional model-based and statistical approaches. In this research, the authors further investigate and compare the performance and results from two major artificial intelligence models, namely, ANNs and LAD, and one pioneer statistical model, PHM over the same two real life prognostics data sets. Such in-depth comparison and review of major CBM techniques was missing in current literature of CBM field.

Improving Photoplethysmographic Measurements Under Motion Artifacts Using Artificial Neural Network for Personal Healthcare

Photoplethysmographic (PPG) measurements are susceptible to motion artifacts (MA) due to movement of the peripheral body parts. In this paper, we present a new approach to identify the MA corrupted PPG beats and then rectify the beat morphology using artificial neural network (ANN). Initially, beat quality assessment was done to identify the clean PPG beats by a pre-trained feedback ANN to generate a reference beat template for each person. The PPG data was decomposed using principal component analysis (PCA) and reconstructed using fixed energy retention. A weight coefficient was assigned for each PPG samples in such a way that when they are multiplied , the modified beat morphology matches the reference template. A particle swarm optimization (PSO) based technique was utilized to select the best weight weight vector coefficients to tune another feedback ANN, fed with a set of significant features generated by an auto encoder from PCA reconstructed data. For real time implementation, this pre-trained ANN was operated in feed-forward mode to directly generate the weight vectors for any subsequent measurements of PPG. The method was validated with PPG data collected from 55 human subjects. An average RMSE of 0.28 and SNR improvement of 14.54 dB was obtained, with an average improvement of 36% and 47% measurement accuracy on crest time and systolic to diastolic peak height ratio respectively. With IEEE Signal Processing Cup 2015 Challenge database, Pearson's correlation coefficient between PPG estimated and ECG derived heart rate was 0.990. The proposed method can be useful for personal health monitoring applications.

Heterogeneous Space–Time Artificial Neural Networks for Space–Time Series Prediction

AbstractSpace–time series prediction plays a key role in the domain of geographic data mining and knowledge discovery. In general, the existing methods of space–time series prediction can be divided into two main categories: statistical machine learning methods. Comparatively, machine leaning methods have obvious advantages with respect to handling nonlinear problems. However, space–time dependence and the heterogeneity of space–time data are not well addressed by the existing machine learning methods. Because of this limitation, an accurate prediction of a space–time series is still a challenging problem. Therefore, in this study, both space–time dependence and heterogeneity are incorporated into the feedback artificial neural network, and heterogeneous space–time artificial neural networks (HSTANNs) are developed for space–time series prediction. First, to handle spatial heterogeneity, space–time series clustering is used to divide the study area into a set of homogeneous sub‐areas. Then, a space–time autocorrelation analysis is employed to explore the space–time dependence structure of the dataset. Finally, a HSTANN is established for each sub‐area. Further, HSTANNs are applied to predict the concentrations of fine particulate matter (PM2.5) in Beijing–Tianjin–Hebei. The experimental results show that when compared with other methods, the accuracy of the forecasting results is considerably improved by using HSTANNs.

A Multi-objective Resource-constrained Project-scheduling Problem Using Mean Field Annealing Neural Networks

The planning and scheduling activities are viewed profoundly important to generate successful plans and to maximize the utilization of scarce resources. Moreover, real life planning problems often involve several objectives that should be simultaneously optimized and real world environment is usually characterized by uncertain and incontrollable information. Thus, finding feasible and efficient plans is a considerable challenge. In this respect, the Multi-Objective Resource-Constrained Project-Scheduling problem (MRCPSP) tries to schedule activities and allocate resources in order to find an efficient course of actions to help the project manager and to optimize several optimization criteria. In this research, A Potts mean field feedback artificial neural network algorithm is developed and explored for the multi-objective resource constrained project scheduling problem. A convenient encoding of inequality constraints is achieved by means of multi-linear penalty function. An approximate energy minimum is obtained by iterating a set of Potts means field equation, is combination with annealing. Priority rule-based heuristics are the most widely used scheduling methods though their performance depends on the characteristics of the projects. To overcome this deficiency, a Potts mean field feedback artificial neural network is designed and integrated into the scheduling scheme so as to automatically select the suitable activity for each stage of project scheduling. Testing on Paterson’s classic test problems and comparison with other exact method how that the proposed Potts mean field annealing neural network based heuristic is able to improve the performance of project scheduling.

Acoustic impedance inversion by feedback artificial neural network

The determination of acoustic impedance distribution from the seismic data field measurement can be expressed as an ill-posed inverse problem. This work deals with the use of the Elman artificial neural network (ANN) (feedback connection) for the seismic data inversion. In the proposed structure the hidden neuron outputs from the previous time step are fed back to their inputs through time delay units; this enables them to process temporal behaviour and provide multi-step-ahead predictions. The ANN architectures and learning rules are presented to allow the best estimate of acoustic impedance from seismic data. The effects of network architectures using 5 to 60 neurons and 10 to 90 neurons in the hidden layer respectively for synthetic and real data on the rate of convergence and prediction accuracy of ANN models are discussed. The behaviour of networks observed on training data is very similar to the one observed on test data. The results obtained clearly prove the feasibility of the proposed method for seismic data inversion by feedback neural networks. Different tests indicate that the back-propagation conjugate gradient algorithm can easily train the proposed Elman ANN structure without getting stuck in local minima.

Real-time Prediction of Dissolved Oxygen in Eutrophic Lake using Feedback Artificial Neural Network Models

Real-time Prediction of Dissolved Oxygen in Eutrophic Lake using Feedback Artificial Neural Network Models

06/00698 Prediction of hourly energy consumption in buildings based on a feedback artificial neural network: González, P. A. and Zamarreo, J. M. Energy and Buildings, 2005, 37, (6), 595–601.

06/00698 Prediction of hourly energy consumption in buildings based on a feedback artificial neural network: González, P. A. and Zamarreo, J. M. Energy and Buildings, 2005, 37, (6), 595–601.

06/00162 Prediction of hourly energy consumption inbuildings based on a feedback artificial neural network: González, P. A. and Zamarreño, J. M. Energy and Buildings, 2005, 37, (6), 595–601

06/00162 Prediction of hourly energy consumption inbuildings based on a feedback artificial neural network: González, P. A. and Zamarreño, J. M. Energy and Buildings, 2005, 37, (6), 595–601

Prediction of hourly energy consumption in buildings based on a feedback artificial neural network

In this paper a new approach for short-term load prediction in buildings is shown. The method is based on a special kind of artificial neural network (ANN), which feeds back a part of its outputs. This ANN is trained by means of a hybrid algorithm. The new system uses current and forecasted values of temperature, the current load and the hour and the day as inputs. The performance of this predictor was evaluated using real data and results from international contests. The achieved results demonstrate the high precision reached with this system.

An efficient mean field approach to the set covering problem

A mean field feedback artificial neural network (ANN) algorithm is developed and explored for the set covering problem. A convenient encoding of the inequality constraints is achieved by means of a multilinear penalty function. An approximate energy minimum is obtained by iterating a set of mean field equations, in combination with annealing. The approach is numerically tested against a set of publicly available test problems with sizes ranging up to 5×10 3 rows and 10 6 columns. When comparing the performance with exact results for sizes where these are available, the approach yields results within a few percent from the optimal solutions. Comparisons with other approximate methods also come out well, in particular given the very low CPU consumption required – typically a few seconds. Arbitrary problems can be processed using the algorithm via a public domain server.

Long-Term Forecasting of Solar Activity Indices Using Neural Networks

Using artificial neural networks (ANN), we study the possibility for long-term forecasting of the annual mean Wolf numbers and the monthly average solar radiation flux at 2800 MHz. A feedback ANN with error backpropagation was designed and implemented for this purpose. The software allows one to vary the number of input parameters and neurons and the values of the training parameters. The forecast error is calculated and the actual data are graphically compared to the predicted ones. The annual Wolf number was forecasted directly one year ahead using an auxiliary training (“warming-up”) of the ANN by the previous 18 values of the annual Wolf number entering the training sequence. The prediction efficiency was 92%. Adding the coronal index and the annual solar-radiation flux (i.e., the SF index) to the input parameters leads to some improvement of the forecast. The iterative long-term forecast of the annual Wolf number for 1986-2000 yielded an efficiency of 71%. Using the direct and iterative techniques, the annual Wolf number was forecasted for the rest of the 23rd and the beginning of the 24th cycles (2000-2010).

Nonlinear Prediction of River Water-Stages by Feedback Artificial Neural Network

The feedback artificial neural network model (FBANNM) was applied to the prediction of the water-stages in a tidal river. The difference between a feed forward artificial neural network model and a FBANNM was investigated. A simple genetic algorithm (SGA) was then incorporated into a FBANNM to help search for the optimal network structure, especially the unit numbers of an input layer and a hidden layer. It was concluded that the FBANNM was a useful tool in the short-term prediction of the water-stages that had a strong autocorrelation due to tidal motion. The optimal network structure of the FBANNM was effectively determined by the SGA incorporating the fitness defined by Akaike's Information Criterion.

Unsupervised neural method for temperature forecasting

This article presents the results of using a novel Negative Feedback Artificial Neural Network for extraction of models of the thermal structure of oceanographic water masses and to forecast time series in real time. The results obtained using this model are compared with those obtained using a Linear Regression and an ARIMA model. The article presents the Negative Feedback Artificial Neural Network, shows how it extracts the model behind the data set and discuses the Artificial Neural Network’s forecasting abilities.