The era of artificial neural network (ANN) began with a simplified application in many fields and remarkable success in pattern recognition (PR) even in manufacturing industries. Although significant progress achieved and surveyed in addressing ANN application to PR challenges, nevertheless, some problems are yet to be resolved like whimsical orientation (the unknown path that cannot be accurately calculated due to its directional position). Other problem includes; object classification, location, scaling, neurons behavior analysis in hidden layers, rule, and template matching. Also, the lack of extant literature on the issues associated with ANN application to PR seems to slow down research focus and progress in the field. Hence, there is a need for state-of-the-art in neural networks application to PR to urgently address the abovehighlights problems for more successes. The study furnishes readers with a clearer understanding of the current, and new trend in ANN models that effectively addresses PR challenges to enable research focus and topics. Similarly, the comprehensive review reveals the diverse areas of the success of ANN models and their application to PR. In evaluating the performance of ANN models, some statistical indicators for measuring the performance of the ANN model in many studies were adopted. Such as the use of mean absolute percentage error (MAPE), mean absolute error (MAE), root mean squared error (RMSE), and variance of absolute percentage error (VAPE). The result shows that the current ANN models such as GAN, SAE, DBN, RBM, RNN, RBFN, PNN, CNN, SLP, MLP, MLNN, Reservoir computing, and Transformer models are performing excellently in their application to PR tasks. Therefore, the study recommends the research focus on current models and the development of new models concurrently for more successes in the field.INDEX TERMS Artificial neural networks, application to pattern recognition, feedforward neural networks, feedback neural networks, hybrid models.
This paper investigates the Impact of relative humidity, varying the concentrations of water-soluble aerosol particle concentrations (WASO), Mineral Nuclei Mode Aerosols Particle Concentration (MINN), mineral accumulation mode, nonspherical (MIAN) aerosol particles concentrations and Mineral Coarse Mode Aerosols Particle Concentration (MICN) on the visibility and particles size distribution of desert aerosols based on microphysical properties of desert aerosols. The microphysical properties (the extinction coefficients, volume mix ratios, dry mode radii and wet mode radii) were extracted from Optical Properties of Aerosols and Clouds (OPAC 4.0) at eight relative humidities, RHs (00 to 99%) and at the spectral visible range of 0.4-0.8mm, the concentrations were varied to obtain five different models for each above-mentioned component. Regression analysis of some standard equations were used to determine the Angstrom exponent (α), the turbidity coefficient (β), the curvature (α2), humidification factor (), the mean exponent of aerosol growth curve (µ) and the mean exponent of aerosol size distributions (n). The values of angstrom exponent (α) were observed to be less than 1 throughout the five models at all RHs for the four studied components, and this signifies the dominance of coarse mode particles over fine mode particles. But the magnitude of the angstrom exponent (α) fluctuates all through the studied components except for WASO which increased with the increase in RH across the models and this also signifies the dominance of coarse mode particles with some traces of fine mode particles. The investigation also revealed that the curvature (α2) has both monomodal (negative signs) and bimodal (positive signs) types of distributions all through the five models and this also signifies the dominance of coarse mode particles with some traces of fine mode particles across the individual models for all the studied components. it was also found that the visibility decreased with the increase in RH and increased with the increase in wavelength. The investigation further revealed that the turbidity coefficient (β) fluctuates with the increase in RH and the particles concentrations, and this might be due to major coagulation and sedimentation. The analysis further found that there is a direct inverse power relation between the humidification factor and the mean exponent of aerosols size distribution with the mean exponent of aerosols growth curve. It was also found that as the magnitude of µ increased for MIAN, MINN and MICN, the effective hygroscopic growth decreased. For WASO, it was found that as the magnitude of µ decreased, the effective hygroscopic growth increased with the increase in particles concentrations and RH. The decreased in the magnitude of µ for WASO might be due to the fact that as we increase the non-hygroscopic particles, we decrease the deliquescence. The mean exponent of aerosol size distribution (n) being less than 3 shows foggy condition of the desert atmosphere the four investigated components and five studied models.
This study investigates the most accurate sunshine and temperature dependent models for estimating global solar radiation over Makurdi and Ibadan situated in the Guinea savannah of Nigeria by comparing nine (9) different existing sunshine dependent models. The study also proposed two temperature dependent models that took the form of quadratic logarithmic and quadratic exponential and were compared to three existing temperature dependent models (Chen, Hargreaves and Samani (HS) and Garcia). The measured monthly average daily global solar radiation, sunshine hours, maximum and minimum temperature meteorological parameters during the period of thirty one (1980-2010) years was utilized and the accuracy of the sunshine and temperature dependent models to ascertain the most suitable models in each location were tested using seven various statistical validation indicators of coefficient of determination (R 2), Mean Bias Error (MBE), Root Mean Square Error (RMSE), Mean Percentage Error (MPE), t-test, Nash-Sutcliffe Equation (NSE) and Index of Agreement (IA). The results revealed that the exponent sunshine dependent model proposed by Bakirci and the linear exponential sunshine dependent model proposed by Bakirci were found more accurate for estimating global solar radiation in Makurdi and Ibadan respectively. The proposed quadratic logarithmic and quadratic exponential temperature dependent models were found more suitable for estimating global solar radiation in Makurdi and Ibadan respectively. These recommended models can be found appropriate, if properly calibrated in regions with similar climatic information. The HS temperature dependent model evaluated in this study for Ibadan was compared with those available in literatures and was found more suitable. Furthermore, the most suitable sunshine dependent model was found more suitable for global solar radiation estimation when compared to the most suitable temperature dependent model in each of the studied locations and this was testified from the figures of the comparison between the measured and estimated sunshine and temperature dependent models as the sunshine dependent models depicts the best fitting with the measured global solar radiation data.
In this study, five different temperature dependent models were proposed and compared with three existing temperature dependent models (Chen, Hargreaves and Samani (HS) and Garcia) using measured monthly average daily global solar radiation, maximum and minimum temperature meteorological parameters during the period of thirty one (1980 -2010) years. The comparison assessment using seven different statistical validation indices of coefficient of determination (R 2 ), Mean Bias Error (MBE), Root Mean Square Error (RMSE), Mean Percentage Error (MPE), ttest, Nash -Sutcliffe Equation (NSE) andIndex of Agreement (IA) was employed to determine the most accurate model for estimating global solar radiation in the five tropical locations situated in the coastal climatic zone of Nigeria. It was found that in each of the locations under investigation the proposed temperature dependent models were reported more suitable for global solar radiation estimation. In Akure, Ogoja, Ikeja, Benin and Owerri; the proposed quadratic logarithmic, linear exponential, multiple linear, quadratic (exponential 2) and quadratic (exponential 1) temperature dependent models respectively were found more accurate and can be applied to locations with comparable weather condition, if properly calibrated against the local data. The HS and Garcia temperature dependent models evaluated in this study for Ikeja was compared with those available in literature and was found more accurate. The figures comparing the measured and estimated temperature dependent models indicates that the most accurate models in each location exhibit the best fitting with the measured global solar radiation data.
No abstract
In this study, time series statistical analysis was carried out on the monthly average daily meteorological parameters of global solar radiation, sunshine hours, wind speed, mean temperature, rainfall, cloud cover and relative humidity during the period of thirty one years (1980 – 2010) using IBM SPSS Statistics version 20 with expert modeler to determine the level, trend and seasonal variations for Ogoja and Maiduguri. Seasonal Auto Regressive Integrated Moving Average models were determined for the two locations along with their respective statistical indicators of coefficient of determination, Root Mean Square Error, Mean Absolute Percentage Error and Mean Absolute Error and are found suitable for one step ahead forecast for the studied area. The factor analysis (empirical orthogonal transformation) and descriptive statistical analysis was also carried out for the study areas under investigation. The results indicated that the model type for all the meteorological parameters for Ogoja is simple seasonal while that for Maiduguri is simple seasonal except for rainfall and cloud cover with winter’s additive and ARIMA models respectively. The correlation matrix obtained from the factor analysis for the studied area indicated that the global solar radiation and wind speed are more correlated with the mean temperature. The sunshine hours and mean temperature are more correlated with the global solar radiation. The rainfall is more correlated with the relative humidity; similarly, the relative humidity is more correlated with the rainfall. However, the cloud cover is more correlated to the rainfall for Ogoja while for Maiduguri the cloud cover is more correlated to the relative humidity. The component matrix analysis revealed that two seasons are identified for Ogoja; the rainy and dry seasons while for Maiduguri three seasons are identified; the rainy, cool dry (harmattan) and hot dry seasons. The skewness and kurtosis test for Ogoja indicated that the global solar radiation, sunshine hours, cloud cover and relative humidity are negatively skewed and the wind speed, mean temperature and rainfall are positively skewed while the global solar radiation, sunshine hours, wind speed, cloud cover and relative humidity indicates possibility of a leptokurtic distribution and the mean temperature and rainfall indicates possibility of a platykurtic distribution. The skewness and kurtosis for Maiduguri indicated that the solar radiation, rainfall and relative humidity are positively skewed and the sunshine hours, wind speed, mean temperature and cloud cover are negatively skewed while the global solar radiation, rainfall and cloud cover indicates possibility of a leptokurtic distribution and the sunshine hours, wind speed, mean temperature and relative humidity indicates possibility of a platykurtic distribution.
The performances of sunshine, temperature and multivariate models for the estimation of global solar radiation for Sokoto (Latitude 13.020N, Longitude 05.250E and 350.8 m asl) located in the Sahelian region in Nigeria were evaluated using measured monthly average daily global solar radiation, maximum and minimum temperatures, sunshine hours, rainfall, wind speed, cloud cover and relative humidity meteorological data during the period of thirty one years (1980-2010). The comparison assessment of the models was carried out using statistical indices of coefficient of determination (R2), Mean Bias Error (MBE), Root Mean Square Error (RMSE), Mean Percentage Error (MPE), t – test, Nash – Sutcliffe Equation (NSE) and Index of Agreement (IA). For the sunshine based models, a total of ten (10) models were developed, nine (9) existing and one author’s sunshine based model. For the temperature based models, a total of four (4) models were developed, three (3) existing and one author’s temperature based model. The results of the existing and newly developed author’s sunshine and temperature based models were compared and the best empirical model was identified and recommended. The results indicated that the author’s quadratic sunshine based model involving the latitude and the exponent temperature based models are found more suitable for global solar radiation estimation in Sokoto. The evaluated existing Ångström type sunshine based model for the location was compared with those available in literature from other studies and was found more suitable for estimating global solar radiation. Comparing the most suitable sunshine and temperature based models revealed that the temperature based models is more appropriate in the location. The developed multivariate regression models are found suitable as evaluation depends on the available combination of the meteorological parameters based on two to six variable correlations. The recommended models are found suitable for estimating global solar radiation in Sokoto and regions with similar climatic information with higher accuracy and climatic variability.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.