Transfer Function Tansig Research Articles

Enhancing Cloud Data Security using Artificial Neural Networks for Users’ Account Hijacking Security Threats

Objectives: To ensure the security of passwords of cloud users' accounts that cannot be decrypted easily by any software or hackers. Methods: In this manuscript, we have designed an experimental setup using a feed-forward back-propagation algorithm of Artificial Neural Networks techniques to ensure cloud data security. For this purpose, we have utilized password-based datasets created by us. 70% of the datasets are allocated for training and 30% for testing and validation purposes. In this training, TRAINLM training function, LEARNGDM adaptive function, performance function is MSE, and PURELIN and TANSIG transfer function to transfer the neurons from input to hidden layer and hidden to the output layer has been used. The minimum learning rate is set to 0.001. Findings: A username and password are required to access cloud services. A cloud-based storage system is used to store login credentials. Due to inadequate security, attackers use hacking techniques to gain access to users’ accounts. Attackers steal data, resources, or services from these accounts. To ensure the security of passwords of cloud users' accounts, we have designed an experimental setup using a feed-forward back-propagation algorithm of neural network techniques. Through this approach, the passwords are stored in a weight matrix, which is a multi-dimensional structure. Novelty: The dimensions of the weight matrix are obscured, making it impossible for the hackers to determine its structure. As a result, we conclude that cloud data is effectively secured on the cloud server. Keywords: Artificial Neural Networks, Cloud Computing, Data Security, Feed-Forward Back-Propagation Algorithm, Machine Learning

An artificial neural network and SCS–CN-based model for runoff estimation: a case study of the Peddavagu watershed

ABSTRACT The accurate prediction of runoff from rainfall events is crucial for effective water resource management, especially in regions with diverse climatic patterns like India. This study proposes a novel approach by integrating the soil conservation service (SCS)–curve number (CN) method with artificial neural networks (ANNs) to model rainfall–runoff relationships. In this research, an SCS–CN method is utilized to estimate initial runoff volumes, accounting for local soil and land-cover characteristics. Subsequently, an ANN-based model is developed to capture the complex nonlinear relationships between rainfall inputs and runoff outputs. Taking the rainfall of the watershed as the inputs, an ANN model was developed in MATLAB for runoff simulation at the main outlet of the Peddavagu watershed. A feed-forward back-propagation method is employed in the ANN model. The architecture with a 1-10-1 configuration based on tan–sig transfer function performed well in terms of MSE 0.019. The model efficiency was satisfactory with the coefficient of correlation (R), 0.96 for training, 0.98 for validation, and 0.98 for testing period. The overall value of R (0.96) indicates the utility of this ANN–SCS-based coupled model for rainfall–runoff simulation.

Effect of foaming agents and dilution ratio on physicochemical and bioactive compounds profile of dried palmyra pulp

The study was carried out to observe the effect of glycerol monostearate (1.0 %, 2.0 %, and 3.0 %), soy protein isolate (0.5 %, 1.0 %, and 1.5 %) and dilution ratio (1:1, 1:1.5) on foam characteristics at whipping time of 4 min. All the samples were incorporated with 0.5 % methyl cellulose (MC) as foam stabiliser and 5 % maltodextrin (MD) as drying aid. The effect of different drying air temperatures (60 °C and 70 °C) at foam thickness of 4 mm on phytochemical, biochemical and functional quality attributes was studied. The efficacy of artificial neural network (ANN) on foam-mat drying kinetics was tested. Foam expansion of the palmyra pulp increased to 108 % when added with 2 % GMS and diluted to 1:1.5. The increase was even more up to 138 % when the same diluted pulp was added with 1.5 % SPI. On the contrary, the foam retention and the foam stability were reduced at a higher dilution ratio. GMS (2 %) or SPI (1 %), each diluted at a 1:1 ratio, exhibited better foaming and colour characteristics. Drying was faster in pulp foamed with SPI (1 %) than in pulp incorporated with GMS (2 %). Non-foamed pulp showed lower drying rates and produced a compact sheet-like mat with a relatively harder and sticky texture. Effective moisture diffusivity values ranged from 1.820 × 10−8 to 2.721 × 10−8 (m2/min) and increased with an increase in the drying temperature. The tansig transfer function of ANN modelling could best predict the moisture ratio with drying time for all the foamed and non-foamed samples. Quality analysis showed that the palmyra pulp foamed with 0.5 % MC, 5 %, MD, and 1 % SPI, diluted at a 1:1 ratio, whipped for 4 min, and dried at 70 °C with foam thickness of 4 mm could produce the powder with best quality attributes. The developed powder was found to possess 79.341 ± 0.998 mg GAE/100 g of total phenolic content, 72.669 ± 0.964 % of antioxidant activity, 60.526 ± 0.975 mg/100 g of ascorbic acid content, 35.287 ± 0.973 % of reducing sugar, 15661 ± 192 µg/100 g of β-carotene with water absorption and hygroscopicity of 2.374 ± 0.827 g/g and 38.487 ± 1.020 % respectively.

Investigating the Effect of Packaging Conditions on the Properties of Peeled Garlic by Using Artificial Neural Network (ANN)

ABSTRACTThis study investigated the effect of packaging conditions on the properties of peeled garlic during storage, and the results have been evaluated using statistical analysis and artificial neural network (ANN). Peeled garlic was packed with polyethylene (PE) film and polyethylene film equipped with nanoparticles (2% nanoclay) and filled into the packages using ambient and modified atmospheres (1% O2, 5% CO2 and 94% N2). A group of packages was also packed under vacuum conditions. The packaged samples were stored at 25°C, 4°C and −18°C for 35 days. Colour indices (a*, b* and L*), chemical properties (pH and TSS) and mechanical properties (Fmax and Emod) of the peeled garlic were measured during the storage time. The final results showed that the use of nanofilm and modified atmosphere had a positive effect on maintaining the quality of peeled garlic during the storage. On the other hand, the temperature changes showed that the freezing temperature had a negative effect on the garlic quality (properties) during the storage period. The statistical analysis results of the data showed the significant effect of treatments and their interactions on properties at levels of 1% and 5%. The results of ANN showed that the peeled garlic properties (physical, chemical and mechanical) could be predicted with the highest performance scores. The most successful ANN models were identified for each property, with the Trainbr learning algorithm and Tansig transfer function yielding the highest prediction scores for physical (R2 > 0.90) and chemical properties; on the other hand, Logsig was most successful for mechanical properties (R2 > 0.84).

Land surface temperature prediction with dual satellites and BPNN: a comparative transfer function analysis

ABSTRACT Driven by global sustainability goals, understanding land surface temperature (LST) in urban thermal environments (UTE) is crucial. This study analyses remotely sensed LST data from Aqua and Terra satellites in a rapidly growing non-tier Indian city. It uniquely integrates remote sensing and soft computational analysis to predict daytime LST using artificial neural networks (ANN). The study is categorized based on transfer functions and hyper-parameters to enhance the comprehension of LST prediction and simulation scenarios by employing Back Propagation Neural Network (BPNN) model. Results indicate that the tansig transfer function yields the best performance overall in Aqua and Terra LST prediction, while purelin performs the least effectively. This study provides evidence that soft computing techniques effectively estimate LST data, offering a valuable solution for data scarcity issues. However, the findings are specific to the study area and may vary elsewhere. Exploring alternative methods and incorporating data from other areas could potentially improve accuracy and overall performance. Future research could focus on investigating the mechanisms behind different methods and their interactions with various factors. Additionally, integrating other variables like vegetation index, soil moisture, and others could contribute to a more holistic understanding of LST dynamics and enhance predictive capabilities.

Tribological Behaviour of Hypereutectic Al-Si Composites: A Multi-Response Optimisation Approach with ANN and Taguchi Grey Method

An optimisation model for small datasets was applied to thixocasted/compocasted composites and hybrid composites with hypereutectic Al-18Si base alloys. Composites were produced with the addition of Al2O3 (36 µm/25 nm) or SiC (40 µm) particles. Based on the design of experiment, tribological tests were performed on the tribometer with block-on-disc contact geometry for normal loads of 100 and 200 N, a sliding speed of 0.5 m/s, and a sliding distance of 1000 m. For the prediction of the tribological behaviour of composites, artificial neural networks (ANNs) were used. Three inputs were considered for ANN training: type of reinforcement (base alloy, Al2O3 and SiC), amount of Al2O3 nano-reinforcement (0 and 0.5 wt.%), and load (100 and 200 N). Various ANNs were applied, and the best ANN for wear rate (WR), with an overall regression coefficient of 0.99484, was a network with architecture 3-15-1 and a logsig (logarithmic sigmoid) transfer function. For coefficient of friction (CoF), the best ANN was the one with architecture 3-6-1 and a tansig (hyperbolic tangent sigmoid) transfer function and had an overall regression coefficient of 0.93096. To investigate the potential of ANN for the prediction of two outputs simultaneously, an ANN was trained, and the best results were from network 3-5-2 with a logsig transfer function and overall regression coefficient of 0.99776, but the predicted values for CoF in this case did not show good correlation with experimental results. After the selection of the best ANNs, the Taguchi grey multi-response optimisation of WR and CoF was performed for the same combination of factors as the ANNs. For optimal WR and CoF, the combination of factors was as follows: composite with 3 wt.% Al2O3 micro-reinforcement, 0.5 wt.% Al2O3 nano-reinforcement, and a load of 100 N. The results show that developed ANN, the Taguchi method, and the Taguchi grey method can, with high reliability, be used for the optimisation of wear rate and coefficient of friction of hypereutectic Al-Si composites. Microstructural investigations of worn surfaces were performed, and the wear mechanism for all tested materials was light abrasion and adhesion. The findings from this research can contribute to the future development of hypereutectic Al-Si composites.

Using artificial neural networks to predict the reference evapotranspiration

Artificial neural network models (ANNs) were used in this study to predict reference evapotranspiration ( ETo) using climatic data from the meteorological station at the test station in Kafr El-Sheikh Governorate as inputs and reference evaporation values computed using the Penman–Monteith (PM) equation. These datasets were used to train and test seven different ANN models that included different combinations of the five diurnal meteorological variables used in this study, namely, maximum and minimum air temperature ( Tmax and Tmin), dew point temperature ( Tdw), wind speed ( u), and precipitation (P), how well artificial neural networks could predict ETo values. A feed- forward multi-layer artificial neural network was used as the optimization algorithm. Using the tansig transfer function, the final architected has a 6-5-1 structure with 6 neurons in the input layer, 5 neurons in the hidden layer, and 1 neuron in the output layer that corresponds to the reference evapotranspiration. The root mean square error ( RMSE) of 0.1295 mm∙day –1 and the correlation coefficient ( r) of 0.996 are estimated by artificial neural network ETo models. When fewer inputs are used, ETo values are affected. When three separate variables were employed, the RMSE test values were 0.379 and 0.411 mm∙day –1 and r values of 0.971 and 0.966, respectively, and when two input variables were used, the RMSE test was 0.595 mm∙day –1 and the r of 0.927. The study found that including the time indicator as an input to all groups increases the prediction of ETo values significantly, and that including the rain factor has no effect on network performance. Then, using the Penman–Monteith method to estimate the missing variables by using the ETo calculator the normalised root mean squared error ( NRMSE) reached about 30% to predict ETo if all data except temperature is calculated, while the NRMSE reached about of 13.6% when used ANN to predict ETo using variables of temperature only.

Streamflow forecasting for the Hunza river basin using ANN, RNN, and ANFIS models

Abstract Streamflow forecasting is essential for planning, designing, and managing watershed systems. This research study investigates the use of artificial neural networks (ANN), recurrent neural networks (RNN), and adaptive neuro-fuzzy inference systems (ANFIS) for monthly streamflow forecasting in the Hunza River Basin of Pakistan. Different models were developed using precipitation, temperature, and discharge data. Two statistical performance indicators, i.e., root mean square error (RMSE) and coefficient of determination (R2), were used to assess the performance of machine learning techniques. Based on these performance indicators, the ANN model predicts monthly streamflow more accurately than the RNN and ANFIS models. To assess the performance of the ANN model, three architectures were used, namely 2-1-1, 2-2-1, and 2-3-1. The ANN architecture with a 2-3-1 configuration had higher R2 values of 0.9522 and 0.96998 for the training and testing phases, respectively. For each RNN architecture, three transfer functions were used, namely Tan-sig, Log-sig, and Purelin. The architecture with a 2-1-1 configuration based on tan-sig transfer function performed well in terms of R2 values, which were 0.7838 and 0.8439 for the training and testing phases, respectively. For the ANFIS model, the R2 values were 0.7023 and 0.7538 for both the training and testing phases, respectively. Overall, the findings suggest that the ANN model with a 2-3-1 architecture is the most effective for predicting monthly streamflow in the Hunza River Basin. This research can be helpful for planning, designing, and managing watershed systems, particularly in regions where streamflow forecasting is crucial for effective water resource management.

Levenberg–Marquardt Training Technique Analysis of Thermally Radiative and Chemically Reactive Stagnation Point Flow of Non-Newtonian Fluid with Temperature Dependent Thermal Conductivity

We have examined the magnetized stagnation point flow of non-Newtonian fluid towards an inclined cylindrical surface. The mixed convection, thermal radiation, viscous dissipation, heat generation, first-order chemical reaction, and temperature-dependent thermal conductivity are the physical effects being carried for better novelty. Mathematical equations are constructed for four different flow regimes. The shooting method is used to evaluate the heat transfer coefficient at the cylindrical surface with and without heat generation/thermal radiation effects. For better examination, we have constructed artificial neural networking models with the aid of the Levenberg–Marquardt training technique and Purelin and Tan-Sig transfer functions. The Nusselt number strength is greater for fluctuations in the Casson fluid parameter, Prandtl number, heat generation, curvature, and Eckert number when thermal radiations are present.

FPGA Tabanlı LogSig ve TanSig Transfer Fonksiyonlarının IQ-Math Sayı Standardında Tasarımı ve Gerçeklenmesi

Yapay Sinir Ağları (YSA), günümüzde sinyal işleme, optimizasyon, tahmin, karar verme ve kontrol gibi bir çok mühendislik alanında yoğun şekilde kullanılmaktadır. YSA yapılarının çalışmasını doğrudan etkileyen önemli bölümlerinden birisi de Transfer Fonksiyonlarıdır (TF). Doğrusal olmayan TF tasarımlarının gerçek zamanlı tasarımı üstel fonksiyon içerdiğinden oldukça zor bir şekilde gerçekleştirilmektedir. Bu çalışmanın ilk aşamasında, literatürdeki çalışmalardan farklı olarak doğrusal olmayan Logaritmik Sigmoid (LogSig) ve Tanjant Sigmoid (TanSig) TF, 32-bit (16I-16Q) IQ-Math formatında VHDL dilinde tasarlanmıştır. İkinci aşamada, VHDL dilinde FPGA çiplerinde çalışmak üzere örnek bir üç giriş-üç çıkışlı bir YSA (ileri beslemeli) yapısı 32-bit IQ-Math formatında modellenmiştir. Tasarımın gizli katmanında 8 adet nöron, gizli katmanda LogSig ile TanSig TF ve çıkış katmanında ise PureLin TF kullanılmıştır. Örnek YSA tasarımı iki farklı TF tasarımı için ayrı bir testbench dosyası oluşturulmuş ve bu tasarımlar VHDL ile Xilinx ISE DS programı ile test edilmiştir. Elde edilen simülasyon sonuçlarına göre nümerik tabanlı LogSig ve TanSig TF içeren YSA tasarımları için MSE ve RMSE hata analizleri yapılarak sonuçlar sunulmuştur. Ardından her bir tasarım XC7K70T-3FBG676 FPGA (Kintex-7) için sentezlenerek Place-Route prosesi gerçekleştirilmiştir. Place-Route prosesinden elde edilen FPGA çip kaynak kullanımı istatistikleri sunulmuştur. Tasarımlara ait hata analizi sonuçlarına göre YSA-LS (LogSig-tabanlı YSA) tasarımı 8.86E-06 MSE ve YSA-TS (TanSig-tabanlı YSA) tasarımı 7.92E-02 MSE sonuçları elde edilmiştir. Bu çalışmadan elde edilen sonuçlar ile IQ-Math tabanlı LogSig ve TanSig aktivasyon fonksiyonu tasarımlarının gerçek zamanlı YSA uygulamalarında güvenli bir şekilde kullanılabileceği gösterilmiştir.

Aqueous biphasic systems based on ethyl lactate: Molecular interactions and modelling

Aqueous biphasic systems (ABS) based on ethyl lactate are novel green solvent systems that are biorenewable and biodegradable with the potential to replace currently used hazardous organic solvents. Models to correlate and predict binodal curves of these systems are crucial for the design of separation processes but are currently nonexistent. Here, we report the development of two empirical models based on Merchuk’s equation and the Effective Excluded Volume model for ABS composed of ethyl lactate, water and a salt (K3PO4, K2HPO4, K2CO3, Na3C6H5O7, Na2C4H4O6, Na2C4H4O4, K2S2O3, Na2S2O3 and (NH4)2S2O3). Additionally, the use of Artificial Neural Networks (ANN) as a tool to predict binodal curves was explored. An ANN composed of tansig transfer function and five neurons was built using three inputs: mole fraction of salt, molar Gibbs energy of hydration of the salt cation and anion. Furthermore, Fourier-transform infrared-attenuated total reflection spectroscopy was used to reveal the molecular interactions which were used to explain binodal data.

Optimization of Oil Yield from the Macro Algae Spirogyra by Solvent Extraction Process Using RSM and ANN

The present work was done to optimize the process parameters of the oil extraction from the algae species spirogyra by using n-hexane as the solvent using the Soxhlet apparatus. The response surface methodology (RSM) and artificial neural network (ANN) were employed to optimize the particle size of the algae powder, dryness level of the algae powder, solid to solvent ratio, reaction time, and extraction temperature of the oil extraction process. Also, the physiochemical properties of the extracted oil were investigated. The comparative evaluation was done between the RSM and ANN models to select the more precise and accurate model. The coefficient of determination, R 2 of 98.92%, and the mean absolute percentage deviation (MAPD) of 0.492% for ANN revealed that the current model created with a network topology of 3 : 11 : 1 with tansig (hyperbolic tangent sigmoid) transfer function in the input layer and purelin (pure linear) transfer function in the output layer trained with trainlm (Levenberg–Marquardt) algorithm found to provide the optimal solution with better accuracy in prediction of the output. The physicochemical properties investigated, such as heating value, flashpoint, density, viscosity, iodine number, acid value, saponification value, and cetane index, showed that the extracted oil from the algae spirogyra species can be used as an alternative fuel.

Artificial neural network analysis of the Nusselt number and friction factor of hydrocarbon fuel under supercritical pressure

This paper presents the Nusselt number and friction factor model for hydrocarbon fuel under supercritical pressure in horizontal circular tubes using an artificial neural network (ANN) analysis on the basis of the back propagation algorithm. The derivation of the proposed model relies on a large number of experimental data obtained from the tests performed with the platform of supercritical flow and heat transfer. Different topology structures, training algorithms and transfer functions are employed in model optimization. The performance of the optimal ANN model is evaluated with the mean relative error, the determination coefficient, the number of iterations and the convergence time. It is demonstrated that the model has high prediction accuracy when the tansig transfer function, the Levenberg-Marquardt training algorithm and the three-layer topology of 4-9-1 are selected. In addition, the accuracy of the ANN model is observed to be the highest compared with other classic empirical correlations. Mean relative error values of 4.4% and 3.4% have been achieved for modeling of the Nusselt number and friction factor respectively over the whole experimental data set. The ANN model established in this paper is shown to have an excellent performance in learning ability and generalization for characterizing the flow and heat transfer law of hydrocarbon fuel, which can provide an alternative approach for the future study of supercritical fluid characteristics and the associated engineering applications.

An Artificial Neural Networks model for predicting patients’ mortality due to COVID-19 "CoviSurv2021"

Introduction. COVID-19 is the pandemic of the century with the unusual circumstances it generated. Subsequently, there has been medical and human scarcity of resources leading to the health system collapse, especially in third world countries. Objective. To support the white army in grasping the pandemic behavior, several studies have pointed to the existence of patient-related factors affecting COVID-19 patients’ mortality-risk. In the current study, Artificial Neural Network (ANN) has been employed to predict COVID-19 mortality. Material and methods. In particular, the modeling phase was done using a database of 684 samples collected from Mohamed Seddik Ben Yahia Hospital of Jijel, with antecedent diseases and blood biomarkers data of patients. Firstly, 18 parameters were selected in the input layer based on the literature recommendation and expert medical team consultation. Furthermore, the optimal inputs have been modeled using the ANN, and their performance was assessed through four performance measures (sensitivity, specificity, precision, and accuracy). Results. The comparative study proved the effectiveness of (18-12-2) model trained by Tansig transfer function, which displayed a higher performance in predicting COVID-19 mortality, compared to other models proposed in the literature. Afterward, the proposed optimal model was utilized to develop a GUI public interface by Matlab software. Conclusion. Finally, a reliable and easy-to-use graphical interface is generated in the current study dubbed “CoviSurv2021”. This latter will be very helpful for the medical staff to select priority patients who have upper urgency to be hospitalized, prioritize patients when the hospital is overcrowded, and gain time to provide the care needed.

Prediction of Trypanosoma evansi infection in dromedaries using artificial neural network (ANN)

Surra is caused by Trypanosoma evansi, a flagellated parasite that affects domestic and wild animals. Surra is a neglected tropical disease causing serious problems to camels breed in Algeria. The aim of our study consists to extract the major risk factors that predict T.evansi infection in dromedaries using artificial neural networks. This investigation was conducted on 115 dromedaries from Ghardaïa district, Southern Algeria. The immune trypanolysis test was used to detect antibodies against T. evansi. Firstly, the gamma test has been used to choose optimal input parameters. The obtained results indicate that the age, gender, breed, clinical manifestations history, herd size, as well as the animal activities were the most predictors of T. evansi infection. Afterward, an artificial neural network method has been performed for modelling the proposed optimal inputs and their accuracy was assessed through seven statistical indicators. The comparative study indicates the effectiveness of the (6−9−1) model trained by the Tansig transfer function. The proposed model has demonstrated a good performance: 0.925 for training data and 0.962 for validation data. Furthermore it could be very useful for the rapid intervention of veterinarians as close as possible to the point-of-care (POC).

MULTILAYER PERCEPTRON ARTIFICIAL NEURAL NETWORK MODEL ON ASSESSING EARLY MATHEMATICAL KNOWLEDGE BEHAVIOURS AND TODD-ACTS MOBILE APPLICATION DEVELOPMENT

In modern culture, mathematics is the primary tool for comprehending science, engineering, and economics. Mathematics has historically been viewed as the primary measure of human intellect. Since the early stages, certain industrialised countries have been carefully considering the subject of fostering and generating geniuses among their people. This is because they recognise that individuals learn or remember knowledge the fastest throughout their first four years due to the prefrontal cortex’s resiliency. This vital period of human existence needs careful consideration. Previous study has revealed that a person’s mathematical skills develop from the day he or she is born. According to science, a person’s capacity to acquire math abilities allows them to develop many other talents faster, and infants are no exception. In this study, we looked at the behaviours or modules that contribute to the development of arithmetic skills or capacities in newborns from birth (0 months) to 4 years old (48 months). In this study, a two-layer neural network with tansig transfer function in the first layer and purelin transfer function in the second layer was used. Because many parents and instructors are focused on the programmes offered at childcare facilities, or the so-called nursery, Montessori, or kindergarten, an innovative mobile application called ‘Todd- Acts’ was created. This mobile application aims to assist parents and teachers with standardised modules that they can practise at home or on their premises, primarily to improve the arithmetic skills of babies in the five critical stages of human life: 0 to 6 months, 6 to 12 months, 12 to 24 months, 24 to 36 months, and 36 to 48 months.

Feed-Forward Back Propagation Network for the prediction of diabetic retinopathy disorder

Some retina disorders mainly involve some blocked blood clots so that, the retinal vessels change their structure, being unable to completely nourish the retina. For an accurate investigation of retina disorders, the extraction of the retinal vessel anatomical structures or lesions is the main task. This paper reports a combination of various features extracted from retinal images, that are further used to train a Feed-Forward Back Propagation Network (FFBPN) as a decision system. The main goal is determining the combination of the appropriate features for more accurate classification of healthy and diseased patients. To achieve this goal, 120 binary images covering both categories of patients that belong to the STARE (Structured Analysis of the Retina) database were analyzed. The input data are the number of ridges, bifurcation, and bridges for retinal vessel pattern recognition. The FFBPNs with 4, 8, 12, 16, and 20 neurons in the hidden layer are trained. The FFBNP architecture with 12 neurons in the hidden layer, using the tansig transfer function in the hidden layer and linear transfer function in the output layer provides the most appropriate model for retinopathy disease classification. The correlation between the number of ridges and bridges computed for healthy patients (as actual values) and the number of ridges and bridges for diabetic patients (as predicted values) provides the best result, a regression coefficient (R) of 0. 8575 and a mean-square error (MSE) of 0.00163.

Viscosity prediction of hydrocarbon binary mixture using an artificial neural network-group contribution method

Abstract In this study, the viscosity of hydrocarbon binary mixtures has been predicted with an artificial neural network and a group contribution method (ANN-GCM) by utilizing various training algorithm including Scaled Conjugate Gradient (SCG), Levenberg-Marquardt (LM), Resilient back Propagation (RP), and Gradient Descent with variable learning rate back propagation (GDX). Moreover, different transfer functions such as Tan-sigmoid (tansig), Log-sigmoid (logsig), and purelin were investigated in hidden and output layer and their effects on network precision were estimated. Accordingly, 796 experimental data points of viscosity of hydrocarbon binary mixture were collected from the literature for a wide range of operating parameters. The temperature, pressure, mole fraction, molecular weight, and structural group of the system were selected as the independent input parameters. The statistical analysis results with R 2 = 0.99 revealed a small value for Average absolute relative deviation (AARD) of 1.288 and Mean square error (MSE) of 0.001018 by comparing the ANN predicted data with experimental data. Neural network configuration was also optimized. Based on the results, the network with one hidden layer and 27 neurons with the Levenberg-Marquardt training algorithm and tansig transfer function for hidden layer along with purelin transfer function for output layer constituted the best network structure. Further, the weights and bias were optimized to minimize the error. Then, the obtained results of the present study were compared with the data from some previous methods. The results suggested that this work can predict the viscosity of hydrocarbon binary mixture with better AARD. In general, the results indicated that combining ANN and GCM model is capable to predict the viscosity of hydrocarbon binary mixtures with a good accuracy.

Modeling CO2 Emission of Middle Eastern Countries Using Intelligent Methods

CO₂ emission is considerably dependent on energy consumption and on share of energy sources as well as on the extent of economic activities. Consequently, these factors must be considered for CO₂ emission prediction for seven middle eastern countries including Iran, Kuwait, United Arab Emirates, Turkey, Saudi Arabia, Iraq and Qatar. In order to propose a predictive model, a Multilayer Perceptron Artificial Neural Network (MLP ANN) is applied. Three transfer functions including logsig, tansig and radial basis functions are utilized in the hidden layer of the network. Moreover, various numbers of neurons are applied in the structure of the models. It is revealed that using MLP ANN makes it possible to accurately predict CO₂ emission of these countries. In addition, it is concluded that using logsig transfer function leads to the highest accuracy with minimum value of mean squared error (MSE) which is followed by the networks with radial basis and tansig transfer functions. The R-squared of the networks with logsig, radial basis and tansig transfer functions are 0.9998, 0.9997 and 0.9996, respectively. Finally, comparison of the proposed model with a similar study, considered five countries in the same region, reveals higher accuracy in term of MSE.

Design and implementation of hydrogen economy using artificial neural network on field programmable gate array

In this study, economic analysis of the hydrogen generation and liquefaction system has been modeled using Multi-Layer Feed-Forward Artificial Neural Network (MLFFANN) and implemented on Field Programmable Gate Array (FPGA). Firstly, the 100X6 data set has been created to be used in the ANN-based modeling of the system using the Engineering Equation Solver (EES) program. This data set has been divided into two data sets as 80X6 for training and 20X6 for testing. The structure of the ANN-based economic analysis of hydrogen generation and liquefaction has been composed of 3 neurons in the input layer, ten neurons in the hidden layer, and three neurons in the output layer. Elliott-2-based TanSig transfer function and Purelin transfer function have been used in the neurons of the hidden layer and the output layer, respectively. Then, the ANN-model has been trained and tested using the Matlab program. The MSE values, 1.40x10E-7 and 2.07x10E-5, have been obtained as the results of the training phase and test phase of the ANN-based system, respectively. After getting fruitful results from training and testing phases, the economic analyses of hydrogen generation and liquation systems have been modeled in VHDL using bias and weight values located in the constructed ANN-based system using Matlab. The modeling has been performed in the Xilinx ISE Design Tools program using a 32-bit IEEE-754-1985 floating-point number standard. Then, the modeled ANN-based economic analysis of the hydrogen generation and liquation system has been implemented on the Xilinx Virtex-7 FPGA chip by performing the Place&Route process. The maximum operating frequency of the ANN-based hydrogen generation and liquefaction economy system implemented on FPGA has been obtained as 281.702 MHz using Xilinx ISE Design Tools.