Figure 5 - uploaded by Muhammad Nadim Hanif
Content may be subject to copyright.
Source publication
![Figure 6. Inflation rate in normalized Scale [-1, +1]](profile/Muhammad-Hanif-73/publication/24116223/figure/fig5/AS:667043237994502@1536046909663/Inflation-rate-in-normalized-Scale-1-1_Q320.jpg)
An artificial neural network (ANN) is an information-processing paradigm that is inspired by the way biological nervous systems, such as the brain, process information. In previous two decades, ANN applications in economics and finance; for such tasks as pattern reorganization, and time series forecasting, have dramatically increased. Many central...
Context in source publication
Similar publications
Many scholars have examined the importance of the money supply to the macroeconomics in developed countries. However, few studies have explored this proposition in developing countries. So, in this paper, annual series data from 2000 to 2016 is applied to analyze the relationship between the money supply (M2) and the macroeconomic variables (the re...
This paper tracks a group of developing countries which started off in the 1960s with a comparable and relatively high aid dependency but followed two different paths in the subsequent four decades: where one sub-group of countries became increasingly aid dependent while the other sub-group nearly exited aid-dependency. It then compares the traject...
Over the past 50 or so years, I have been concerned with the quality of economic forecasts and have written both about the procedures for evaluating these predictions and the results that were obtained from these evaluations. In this paper I provide some perspectives on the issues involved in judging the quality of these forecasts. These include th...
The major focus of this paper is to determine whether the accur acy of German macroeconomic forecasts has improved over time. We examine 1-year-ahead forecasts of real GDP and inflation for 1967 to 2001 made by three major Germ an forecasting groups and the OECD. We examine the accuracy of the forecasts over the entire period and in three sub-perio...
Citations
... The time series must be distinct, stationary, and evenly spaced for the method to function properly [2]. The three most frequent linear stationary Box-Jenkins models are autoregressive (AR), moving average (MA), and autoregressive moving average (ARMA), which combines AR and MA models [4]. The Box-Jenkins technique has a substantial advantage in that it can use past observation values as an explanatory variable. ...
With its seas and water resources, Türkiye's aquaculture industry plays a significant role in both the nation's economy and society's ability to eat healthily. The objectives of this study are to evaluate the level of self-sufficiency in aquaculture production, assess the developments in the aquaculture sector in Türkiye, and estimate the production amount for the next ten years employing the ARIMA (Autoregressive Integrated Moving Average) method using the aquaculture production amounts between 1950 and 2021. Making forecasts for the upcoming years is believed to be beneficial in terms of investment and production planning. The amount of aquaculture production was estimated with the Box-Jenkins ARIMA method. As a result of the analyses performed, the ARIMA (1, 2, 2) model was found to be the most suitable model for forecasting aquaculture production. According to the estimation, it is expected to increase by 17.29% between 2022 and 2031. It is believed that depending on this rise, actions should be taken to expand the aquaculture processing facilities associated with the aquaculture sector.
... In the forward propagation stage, the current state of the artificial neural network contains the values formed at the outputs of the network against the input signals applied to the network. In the back propagation stage, the weights in the circuit are rearranged based on the errors in the outputs [33]. ...
In this study, composite coatings with NiB alloy main structure reinforced with TiC nanoparticles were coated on a stainless steel substrate by electrodeposition method. The microhardness and crystal structures of the produced nanocomposite films were examined and the relations between the obtained results and the production parameters were discussed in detail. In addition, the surface and section morphologies of the coatings were analyzed by SEM and EDS. Furthermore the complex relationship between the experimentally obtained micro-hardness, crystal grain size values and the production parameters was modeled by artificial neural networks (ANN) method. According to the hardness results, nanocomposite coatings microhardness values varied between about 470 HV and 820 HV. In XRD examinations, the crystal grain size values of nanocomposite coatings were found ranging from 6.6 nm to 17.4 nm. From the morphology results, it is understood that the surface structure and coating thicknesses are remarkably affected by the production parameters. Considering the EDS results, it was observed that the alloying with boron and the TiC reinforcement were successfully applied in nanocomposite coatings. With respect to the results obtained with ANN, the best results were obtained in the model with 10 neurons in the hidden layer and the highest error value of 2.02% was achieved for microhardness values. For the crystal grain size, the most successful results were acquired in the model with 12 neurons and the highest error value was obtained as 3.397%.
... In reference [4] Multi-layer Perceptions network is used to estimate the load in short term by using 2 variables; the historical load demand and time. The author of reference [5] used the ANN to forecast electrical power load according to hours in short term. In reference [6] the ANN is used to short term forecast load according to hours, the day of the week and weather data which is made simple as seasons' values. ...
Today, one of most important concerns in electrical power markets and distribution network is supplying the customer demands. In order to manage the market it is necessary to forecast the usage of electrical power in distribution network. The pattern of electrical power usage depends on many different parameters such as the week days, seasons, weather condition and etc. Today, researchers by using an artificial intelligence based on the natural intelligence are trying to forecast the costumers' usage of electrical power. In this Paper it is tried to forecast the electrical power usage according to weather data by using artificial neural network in Bushehr distribution electrical power network and also is tried to find out the pattern of electrical power usage with the dataset which is prepared by real data. The method which has been used here is useful in all kind of power forecasting such as short term, middle term and long term. It can be helpful to manage the distributed generators production schedule and also correction of electrical power usage.
Events in the atmosphere from past to present – wind, precipitation, humidity, temperature – have almost always been the subject of research to create a forecast in regions. The rapid development of the technological field in terms of software and hardware brings methods and techniques to be used in research. One of them is Artificial Neural Networks. In this study, precipitation data were estimated using the Feed Forward Backpropagation method of Artificial Neural Networks method using past data of meteorological parameters, and they were compared with the data of multiple linear regression analysis. Based on these models, six different models were studied, and regression and performance evaluations were made. While the error average of multiple linear regression is 0.2413, this value is 0.076 in artificial neural networks, and the correlation average for both is 0.90. As a result of this study, the best model has a coefficient of determination of 0.95 and an error value of 0.18 in multiple linear regression, as well as a coefficient of certainty of 0.99 and an error value of 0.0438 in artificial neural networks; It has been understood that the 1st model, which has 6 data sets as the input layer, exhibits the best performance.
Bu araştırmada, 45 HRc sertlik değerine sahip AISI 1040 çeliği torna tezgahında işlenmiştir. Kesme hızı, ilerleme ve talaş derinliği parametreleri üçer seviye olarak belirlenmiştir. Deney listesi Taguchi L9 ortagonal dizilim ile oluşturulmuştur. Deneyler CNC kontrollü tornada gerçekleştirilmiştir. Tornalama işlemi sonunda ortalama yüzey pürüzlülüğü (Ra), off-line olarak elde edilmiştir. Elde edilen Ra değerleri Taguchi, çoklu regresyon modeli, yapay sinir ağı ve bulanık mantık ile modellenmiştir. Bu modeller arasındaki yüzdesel fark belirlenmiştir. Taguchi yaklaşık %86,27, çoklu regresyon modeli yaklaşık %85,85, yapay sinir ağı yaklaşık %78,92 ve bulanık mantık yaklaşık %93,86 doğrulukla test sonuçlarını tahmin etmiştir.
Weather forecasting has become an important field of research in the last few decades. In most of the cases the researcher had attempted to establish a linear relationship between the input weather data and the corresponding target data. But with the discovery of nonlinearity in the nature of weather data, the focus has shifted towards the nonlinear prediction of the weather data. Although, there are many literatures in nonlinear statistics for the weather forecasting, most of them required that the nonlinear model be specified before the estimation is done. But since the weather data is nonlinear and follows a very irregular trend, Artificial Neural Network (ANN) has evolved out to be a better technique to bring out the structural relationship between the various entities. The paper examines the applicability of ANN approach by developing effective and reliable nonlinear predictive models for weather analysis also compare and evaluate the performance of the developed models using different transfer functions, hidden layers and neurons to forecast maximum, temperature for 365 days of the year.
In this study, artificial neural network (ANN) for forecasting government size in Iran is applied. The purpose of the study is comparison various architectures, transfer functions and learning algorithms on the operation of network, for this purpose the annual data from 1971-2007 of selected variable are used. Variables are tax income, oil revenue, population, openness, government expenditure, GDP and GDP per capita; these variables are selected based on economic theories. Result shows that networks with various training algorithms and transfer functions have different results. Best architecture is a network with two hidden layer and twelve (12) neuron in hidden layers with hyperbolic tangent transfer function both in hidden and output layers with Quasi -Newton training algorithm. Base on findings in this study suggested in using neural network must be careful in selecting the architecture, transfer function and training algorithms.
Gross Domestic Product (GDP) is a benchmark for economic production conditions of a country. Estimates of economic growth in the coming year in a country has important roles, among others as a benchmark in determining business plans for business entities, and the basis for devising government fiscal policy. Artificial Neural Network (ANN) has been increasingly recognized as a good forecasting tool in various fields. Its nature that can mimic the workings of the human brain makes it flexible for non-linear and non-parametric data. GDP growth forecasting techniques using ANN has been widely used in various countries, such as the United States, Canada, Germany, Austria, Iran, China, Japan and others. In Indonesia, forecasting of GDP is only done by government institutions, namely National Planning Board, using macroeconomic model. In this study, ANN is used as a tool for forecasting GDP growth in Indonesia, using some variables, such as GDP growth in the two previous periods, population growth rate, inflation, exchange rate and political stability and security conditions in Indonesia. Results from this study indicate that ANN forecasts GDP relatively better than the one issued by the government. Further study would be to use ANN to predict other economic indicators.
This paper examines the inflation "pass-through" problem in American monetary policy, defined as the relationship between changes in the growth rates of individual goods and the subsequent economy-wide rate of growth of consumer prices. Granger causality tests robust to structural breaks are used to establish initial relationships. Then, feedforward artificial neural network (ANN) is used to approximate the functional relationship between selected component subindexes and the headline CPI. Moving beyond the ANN "black box," we illustrate how decision rules can be extracted from the network. Our custom decompositional extraction algorithm generates rules in human-readable and machine-executable form (Matlab code). Our procedure provides an additional route, beyond direct Bayesian estimation, for empirical econometric relationships to be embedded in DSGE models. A topic for further research is embedding decision rules within such models.
