Artificial Neural Network for Predicting Indonesian Economic Growth Using Macroeconomics Indicators

The ongoing COVID-19 pandemic process we all face currently has highlighted the fact that digitalization of economic activities is very crucial. Digital economy became even more important after the pandemic. When the governments allocate a greater proportion of Gross Domestic Product on some public services, the lower the proportion spent on other goods and services. For this reason, many countries want to estimate the Gross Domestic Product spent on public services within the scope of public control and risk management. The main goal in this study is to predict Gross Domestic Product per capita based on digital indicators such as fixed-broadband subscriptions, mobile-cellular telephone penetration rate, fixed-telephone subscriptions, internet penetration rate, research and development expenditure and patent applications. Artificial Neural Networks are employed to predict Gross Domestic Product per capita via digital indicators. Artificial Neural Network method is used to estimate the digital economy for 29 OECD countries between 2002–2018. The results demonstrate that Artificial Neural Networks can be utilized effectively in applications of digital economy forecasting. According to the results, coefficient of determination (R2 = 0.92) is very high, meaning that Artificial Neural Networks can be effectively utilized in Gross Domestic Product per capita estimations through digital indicators. This article differs from previous studies as it uses digital economic indicators in predicting Gross Domestic Product per capita by applying Artificial Neural Networks model.

Detecting the different blends of diesel and biodiesel fuels using electronic nose machine coupled ANN and RSM methods

Heat rate of a combined cycle power plant (CCPP) is a parameter that is typically used to assess how efficient a power plant is. In this paper, the CCPP heat rate was predicted using an artificial neural network (ANN) method to support maintenance people in monitoring the efficiency of the CCPP. The ANN method used fuel gas heat input (P1), CO2 percentage (P2), and power output (P3) as input parameters. Approximately 4322 actual operation data are generated from the digital control system (DCS) in a year. These data were used for ANN training and prediction. Seven parameter variations were developed to find the best parameter variation to predict heat rate. The model with one input parameter predicted heat rate with regression R2 values of 0.925, 0.005, and 0.995 for P1, P2, and P3. Combining two parameters as inputs increased accuracy with regression R2 values of 0.970, 0.994, and 0.984 for P1 + P2, P1 + P3, and P2 + P3, respectively. The ANN model that utilized three parameters as input data had the best prediction heat rate data with a regression R2 value of 0.995.

In this study, seismic events in Kula district (Manisa, Turkey) and its vicinity have been investigated and then natural and artificial seismic activities are discriminated. Total of 77 digital vertical component velocity seismograms of seismic activities with M L ≤3.5 magnitude from seismic activity catalogs between 2009 to 2014 recorded by Manisa Kula (KULA) broadband station operated by Bogazici University, Kandilli Observatory and Earthquake Resarch Institute Regional Earthquake- Tsunami Monitoring Center (RETMC) were used in this study. The maximum S-wave and maximum P-wave amplitude ratio (Ratio) of vertical component velocity seismograms and power ratio for (1 and 12 sec.) (Complexity-C) and total signal duration (Duration) of the waveform were calculated. The earthquakes and the quarry blasts have been discriminated using linear discriminant function (LDF) and Back Propagation-Feed Forward Neural Networks (BPNNs) that is one of the learning algorithms at the artificial neural networks (ANNs) methods taking correlation between these parameters into consideration. 39 (51%) of the 77 seismic activities were identified as quarry blasts and 38 (49%) of them as earthquakes LDF and ANNs methods have been applied together for the first time for Ratio-C, Ratio-logS and Ratio-duration parameter pairs with the data of Manisa and surroundings, and earthquakes and quarry blasts have been distinguished from each other. LDF and ANNs methods were compared for each pair of parameters. Both of two methods are successful but the ANNs method has higher accuracy percentage values than LDF method when there is sufficient number of data. The accuracy percentages are different for a pair of Ratio versus C, for a pair of Ratio versus logS and for a pair of Ratio versus duration, respectively.

The relativistic mean field (RMF) model with a small number of adjusted parameters has been used successfully in the last thirty years for predictions of various ground-state nuclear properties of nuclei. In this model, Dirac and Klein–Gordon like equations obtained from application of variation principle on phenomenological Lagrangian density are solved iteratively for calculations of nuclear properties of nuclei. For this purpose, parameters such as masses of considered mesons, nucleon–meson coupling constants, and self-couplings of mesons are needed and they are fitted from experimental data. Some parameter sets for RMF model introduced to correct predictions of nuclear properties of nuclei cover nuclidic chart. Besides Artificial Neural Network (ANN) method is used successfully in many field of science as in nuclear physics. ANN is known as a very powerful tool that are used when standard techniques fail to estimate the correlation between the variables. In the present study, ANN method has been employed to check its understanding capability of relations between RMF model parameters and their predictions on the ground-state binding energies of some spherical nuclei. Understanding capability of ANN method for these relations of considered nuclei has been found well. Based on this success, new non-linear parameter set for RMF model called DEFNE by us have been produced by using ANN method. Furthermore, predictions of RMF model with DEFNE parameter set for ground-state binding energies and charge radii of nuclei cover nuclidic chart have been found as in agreement with the available experimental data.

GIS-based landslide susceptibility mapping using analytic hierarchy process and artificial neural network in Jeju (Korea)

Diesel oil is known to be one of the major petroleum products that can pollute water and soil. Soil pollution caused by petroleum hydrocarbons has substantially impacted the environment, especially in the Middle East. In this study, modeling and optimization of hexadecane removal from soil was performed using two pure cultures of Acinetobacter and Acromobacter and consortium culture of both bacterial species using artificial neural network (ANN) method. Then the best ANN structure was proposed based on mean square error (MSE) as well as correlation coefficient (R) for pure cultures of Acinetobacter and Acromobacter as well as their consortium. The results showed that the correlations between the actual data and the data predicted by ANN (R2) in Acromobacter, Acinetobacter and consortium of both cultures were 0.50, 0.47 and 0.63, respectively. Despite the low correlation between the experimental data and the data predicted by the ANN, the correlation coefficient and the precision of ANN for the consortium was higher. As a result, ANN had desirable precision to predict hexadecan removal by the cobsertium culture of Ochromobater and Acintobacter.

This paper employs an artificial neural network (ANN) method to achieve an approximate solution [Formula: see text] of the one-dimensional fractional Rayleigh–Stokes equation with boundary and initial conditions. ANN is a machine learning branch that aims to minimize the loss function, which closely approaches the solution of mathematics equations. By combining the ANN output with the initial and boundary conditions, we can achieve an adequate approximation for this fractional equation. The study utilizes a multi-layer feed-forward neural network algorithm and error backpropagation method with unsupervised learning to minimize the loss function and parameter alteration (weights and biases). The accuracy and effectiveness of the ANN technique were demonstrated through several examples. This method can approximate solutions of the Rayleigh–Stokes equation for more than 10,000 points with considerable accuracy in a short time. A comparison of the results achieved with other existing techniques indicates that the ANN method provides a more appropriate approximation.

Assessing the economic impact of public investment in Malaysia: a case study on MyRapid Transit project using a dynamic computable general equilibrium model

The Impact of Domestic and Direct Foreign Investment on the Economic Growth in Sudan: Evidence from Granger Causality and VAR Framework Dr. Musa Albur Abstract Foreign Direct Investment and Domestic Investment provide a crucial basis for economic development of any country. This study examines the causes and impacts of Real Gross Domestic Product (RGDP), Real Domestic Investment (DI) and Real Foreign Direct Investment (FDI) in Sudan for the period from 1990 to 2011.The importance of this study stems from the vital role of investment (domestic and foreign) in the development process through enhancing economic growth, improving infrastructure and achieving welfare. This study adopted Vector Autoregressive Model and Granger Causality Test (1969). The study depended on secondary data collected from Central Bank of Sudan and Central Bureau of Statistics. Our empirical evidence suggests that the causality directions running positively in the period (1990-2011). There is unidirectional causality of Foreign Direct Investment (FDI) to Real Gross Domestic Product (RGDP), from Real Gross Domestic Product (RGDP) to Foreign Direct Investment (FDI), from Domestic Investment (DI) to Real Gross Domestic Product (RGDP), from real gross domestic product (RGDP) to domestic investment (DI), from foreign direct investment (FDI) to domestic investment (DI), and from domestic investment (DI) to foreign direct investment (FDI). Granger causality results show that there are no statistically significant implications of the independence causality relationship between Domestic Investment( DI) and Real Gross Domestic Product (RGDP), Real Gross Domestic Product(RGDP) to Domestic Investment( DI), Foreign Direct Investment (FDI) ) to Real Gross Domestic Product (RGDP), Real Gross Domestic Product (RGDP) to Foreign Direct Investment (FDI), Foreign Direct Investment (FDI) ) to Domestic Investment(DI), and Domestic Investment ( DI) to Foreign Direct Investment(FDI). The VAR estimation shows that the coefficients of lagged RGDP significant in the regression of the RGDP, the coefficients of lagged DI significant in the regression of the DI and FDI, the coefficients of lagged DI insignificant in the regression of the RGDP, and the coefficients of lagged FDI insignificant in the regression of the RGDP.The study recommends raising more real financial resources for the purpose of investing in economic and social infrastructure as well as in oil exploration. Industrialization is highly recommended for import substitution purpose and for increasing the value added for Sudan's exports to benefit more from international trade. These require encouraging domestic saving, attraction of foreign funds to supplement the domestic component, strengthening foreign relations, and facilitating the investment procedures and thus achieving economic growth in the country. Full Text: PDF DOI: 10.15640/jeds.v7n4a9

The term 'Value Added Tax (VAT)' can be defined as a tax levied (on the value created) at each stage in the process of production and distribution of a good or service. These stages can be import, manufacturing, dealers, wholesalers and retailers etc. Value added tax (VAT) is a tax on the value that a business firm adds to the things it buys from other firms in producing its own product. The main objective of this study is to assess the impact of VAT on GDP, PCON, IMP, GE, GNS, TI and to examine the relationship and causality among the macro economic variables. In model specification only few variables such as Gross Domestic production (GDP), value added tax (VAT), private consumption (PCON), import (IMP), government expenditure (GE), gross national saving (GNS) and total investment (TI) are including many other variables are unable to include. Literature review suggests a growing need for examining extensive study on the contribution of VAT on economic growth. There is lack of macro level studies ascertaining the impact of VAT in economic growth and moreover this study incorporate more important variables as like private consumption, import, government expenditure, gross national saving, disposable personal income and total investment in the study. Some important findings have been obtained. The econometrics results have shown the fact that a positively significant impact of VAT on gross GDP of a country (Model I). Regarding the relationship between private consumption, disposable personal income, value added tax( model 1.4), import, nominal gross domestic production, value added tax (model 1.5), government expenditure, nominal gross domestic production, value added tax(model 1.6), gross national saving , nominal gross domestic production, value added tax(model 1.7), The application of VAR to examine the long run relationship suggest long run relationship and all the explanatory variables are statistically insignificant but all the model are free from the autocorrelation, Heteroskedasticity and residuals are normally distributed which is desirable. There is unidirectional granger cause as like LnGDP to LnVAT, LnGDP to LnGNS and LnTI to LnGDP.

This note reports a trial to establish an ANN (artificial neural network) method applying to EBT3 films of different batches without batch-specific calibration. Based on Pytorch (Facebook, https://pytorch.org/), a feed-forward ANN model was built to convert the pixel values of scanned images from different batches into absorbed dose. Films from different batches exposed to x-ray doses were digitized in transmission mode on an Epson 11000XL scanner for training and testing. The calculated dose map of TPS (radiation therapy planning system) was used as a label (the desired output) for the ANN model. To verify the performance and generalization of the ANN method, a cross-validation experiment was performed. Using the trained ANN method, the scanned images were converted into absorbed dose maps, and the converted dose maps have good agreement with the calculated dose maps from TPS. For films irradiated via the sliding window mode, the MSEs (mean square errors) of the trained batches were less than and the MSEs of the tested batches were less than . For patient intensity-modulated radiotherapy (IMRT) films, the γ(3%, 3 mm) between the dose maps obtained from the trained films and TPS exceeded 97.5%. The γ(3%, 3 mm) between most of the dose maps obtained from the tested films and TPS exceeded 97.0%. This shows that it is feasible to establish a method for EBT3 films from certain batches to convert pixel values into an absorbed dose without batch-specific calibration, and the method can be applied to other cases.

ABSTRACTThis paper proposes a multilayer artificial neural network (ANN) method to predict the probability of default (PD) within a survival analysis framework. The ANN method captures hidden interconnections among covariates that influence PD, potentially leading to improved predictive performance compared to both logit and skewed logit models. To assess the impact of covariates on PD, we introduce a generalized covariate method that accounts for compositional effects among covariates and employ stochastic dominance analysis to rank the importance of covariate effects across both the ANN and logit model approaches. Applying the ANN method to a large dataset of small business loans reveals prediction gains over the logit models. These improvements are evident for short‐term prediction horizons and in reducing type I misclassification errors in the identification of loan defaults, an aspect crucial for effective credit risk management. Regarding the generalized covariate effects, our results suggest that behavior‐related covariates exert the strongest influence on PD. Moreover, we demonstrate that the ANN structure stochastically dominates the logit models for the majority of the covariates examined.

Background: The optimal management of hospitals as the most important centers for providing health services has always been the focus of decision makers and policymakers. The present study aimed to evaluate the technical efficiency of hospitals affiliated to Ardebil University of Medical Sciences using Artificial Neural Network (ANN) method. Methods: The present descriptive, applied, and cross-sectional study was conducted in 2017. The study population consisted of 8 educational and therapeutic centers affiliated to Ardabil University of Medical Sciences and Health Services. Census sampling method was applied to select the participants and researcher-made checklists were used to collect the data. The artificial neural network method was also used to investigate the study objectives. The applied network was a multi-layer prospectron with a Levenberg Marquardt optimization function, a sigmoid tangent transfer function in the middle layer, and a linear function in the output layer. For processing and preparing data, Excel spreadsheet was used and Matlab software were used for analyzing and designing the network. Results: The results showed that the average technical efficiency of the studied hospitals was 0.75. Ardabil Bou Ali, Khalkhal Imam Khomeini, and Meshkinshahr Valiasr hospitals had the highest technical efficiency (1.00). With regard to the hospital bed occupancy rate, Germi Velayat hospital had the lowest efficiency rate (0.75). Furthermore, Parsabad Imam Khomeini hospital had the lowest efficiency in the number of discharged healthy patients (0.69) in 2017. Finally, the improvement space of each variable was calculated to achieve the total technical efficiency. Conclusion: According to the results, one of the factors that decreases the technical efficiency of the educational centers is the low rate of hospital beds' utilization and occupancy rate. In other words, lack of full-capacity operation by the hospital centers and the low rates of active hospital bed imposed costs and consequently reduced the hospitals' performance.

This study forecasts standard of living in Tanzania over the next ten years as measured by the ratio of two rates: (1) economic growth, using real gross domestic product (GDP), to (2) population growth. GDP alone is an insufficient measure of a nation’s well-being. China and India, for example, have high levels of GDP, but the pie is sliced very thin to be shared among the billions of people who live in those two countries. Real GDP per capita measures not only the level of economic activity but also the number of people who must share in the results of that activity. This study uses historical data for Tanzania’s real GDP (i.e., adjusted for inflation) and population to observe the ratio over time (from 1960 to 2011). One discovery is that of a point of inflection at the end of the 20th century, such that GDP per capita rose at an annual rate of just one percent “pre-inflection” and four times that rate “post-inflection.” The study uses standard statistical methods to forecast the variables over the next ten years. Results of the forecast indicate that GDP will continue to grow at a faster rate than will population, with a consequent steady rise in the average standard of living. How the increased prosperity will be distributed, so as to reduce the level of poverty and the disparity of income, remains to be seen.