Feed-forward Artificial Neural Network Model Research Articles

Prediction of gamma ray spectrum for 22Na source by feed forward back propagation ANN model

The radiation has been used in a variety of different fields since its discovery and thus its measurement becomes vital in these industries. Different type detector may be used to measure gamma rays depends on the purposes of measurements. Gamma ray energy spectrum is an important to determine either elemental analysing of a sample or radiation shielding purposes. On the other hand, Artificial Neural Network (ANN) may be used to predict and analysing of gamma-ray spectrum. In this study, gamma ray spectrum from 22Na source detected in NaI (Tl) detector was estimated by ANN. There have been installed ten different ANN models to find the network structure that produces the best predictive value for the gamma ray spectrum NaI (Tl) Detector. Estimation study has been continued with the ANN model with be possessed of lowest error value. ANN model was created by using energy, distance and gamma-rays energy spectrum (called Io) values. In the ANN model developed using the feed forward back propagation algorithm, were used artificial neurons two in the input layer, ten in the hidden layer and one in the output layer. For the case of present work, the experimental data was used 70% for education, 20% for validation and 10% for testing. The estimated values obtained with the ANN model were compared with the experimental results and a good correlation has been found between them (R2 = 0.99).

A deep learning approach to predict the number of [formula omitted]-barriers for intrusion detection over a circular region using wireless sensor networks

Wireless Sensor Networks (WSNs) is a promising technology with enormous applications in almost every walk of life. One of the crucial applications of WSNs is intrusion detection and surveillance at border areas and in the defence establishments. The border areas are stretched over hundreds to thousands of miles, hence, it is not possible to patrol the entire border region. As a result, an enemy may enter from any point absence of surveillance and cause the loss of lives or destroy the military establishments. WSNs can be a feasible solution for the problem of intrusion detection and surveillance at the border areas. Detection of an enemy at the border areas and nearby critical areas such as military cantonments is a time-sensitive task as a delay of a few seconds may have disastrous consequences. Therefore, it becomes imperative to design systems that can identify and detect the enemy as soon as it comes within the range of the deployed system. In this paper, we have proposed a deep learning architecture based on a fully connected feed-forward Artificial Neural Network (ANN) for the accurate prediction of the number of k-barriers for fast intrusion detection and prevention. We have trained and evaluated the feed-forward ANN model using four potential features, namely area of the circular region, sensing range of sensors, transmission range of sensors, and number of sensor for Gaussian and uniform sensor distribution. These features are extracted through Monte Carlo simulation. In doing so, we found that the model accurately predicts the number of k-barriers for both Gaussian and uniform sensor distribution with correlation coefficient (R = 0.78) and Root Mean Square Error (RMSE = 41.15) for the former and R = 0.79 and RMSE = 48.36 for the latter. Further, the proposed approach outperforms the other benchmark algorithms in terms of accuracy and computational time complexity.

Drainage congestion due to road network on the Kosi alluvial Fan, Himalayan Foreland

We use surface soil moisture content as a proxy to assess the effect of drainage congestion due to structural barriers on the alluvial Fan of the Kosi River on the Himalayan Foreland. We used Sentinel-1 satellite images to evaluate the spatial distribution of soil moisture in the proximity of structural barriers (i.e., road network). We applied modified Dubois and a fully connected feed-forward artificial neural network (FC-FF-ANN) models to estimate soil moisture. We observed that the FC-FF-ANN predicts soil moisture more accurately (R = 0.85, RMSE = 0.05 m3/m3, and bias = 0) as compared to the modified Dubois model. Therefore, we have used the soil moisture from the FC-FF-ANN model for further analysis. We identified the road network that traverses on the Kosi Fan horizontally, vertically, and with inclination. We create a buffer of 1 km along either side of the road. Within this, we assessed the spatial distribution of soil moisture. We observed a high concentration of soil moisture near the structural barrier, and decreases gradually as we move farther in either direction across the orientation of the road. The impact of structural barriers on the spatial distribution of soil moisture is prominent in a range between 300 to 750 m within the road buffer. This study is a step towards assessing the effect of structural interventions on drainage congestion and flood inundation.

Ultrasound enhanced butyric acid-lauric acid designer lipid synthesis: Based on artificial neural network and changes in enzymatic structure

Ultrasound is a green technology for intensifying enzymatic reactions. In this study, an ultrasonic water bath with equipment parameters of 28 kHz, 1750.1 W/m2, 60% duty cycle was used to assist the synthesis of butyric acid-lauric acid designer lipid (BLDL), which was catalyzed by Lipozyme 435. A convincing three-layer feed-forward artificial neural network (ANN) model was established (R2 = 0.949, RMSE = 4.759, ADD = 7.329) to accurately predict the optimal parameters combination, which was described as 13.72 mL reaction volume, 15.49% enzyme loading, 0.253 substrate molar ratio (tributyrin/lauric acid), 56.58 °C reaction temperature and 120 min reaction time. The ultrasonic assistance increased actual butyric acid conversion rate by 11.38%, and also enhanced the consumption rate of tributyrin and lauric acid during the reaction. Meanwhile, the esterification activity of Lipozyme 435 was enhanced and its effectiveness up to 6 cycles. Structurally, ultrasound assistance significantly disrupted the secondary structure of the Lipozyme 435: reduced the content of α-helices, increased the content of β-sheet and β-turn. In addition, sonication caused an increase in crevice and micro-damage on the surface of the immobilized enzyme. In conclusion, low-intensity ultrasound at 28 kHz improved the synthesis efficiency of BLDL, which was scientifically predicted by ANN model, and the change of enzyme structure may be the vital reason for ultrasound enhanced reaction. However, the effect of ultrasound on immobilized enzymes’ activity needs to be further explored.

Using feed-forward perceptron Artificial Neural Network (ANN) model to determine the rolling force, power and slip of the tandem cold rolling

In this paper, an Artificial Neural Network (ANN) is used to investigate the influence of rolling parameters such as thickness reduction, inter-strand tension, rolling speed and friction on the rolling force, rolling power, and slip of tandem cold rolling. For this reason, the rolling power was derived for 195 various experiments through a series of observation tests. The network is trained and tested using real data collected from a practical tandem rolling line. The best topology of the ANN is determined by Broyden–Fletcher–Goldfarb–Shanno (BFGS) training algorithm and error, and nine neurons in the hidden layer had the best performance. The average of the training, testing, and validating correlation coefficients data sets are mentioned 0.947, 0.924, and 0.943, respectively. The obtained results show MSE value 4.2 × 10−4 for predicting slip. In addition, the effect of friction and angular velocity condition on the cold rolling critical slip phenomena are investigated. The results show that ANNs can accurately predict the cold rolling parameters considered in this study.

Determination of tool tip steady-state temperature in dry turning process based on artificial neural network

Effective and accurate measurement of cutting temperature of the tool tip is of great significance in the machining fields. However, the current measuring methods, including the embedded thermocouple and thermography, have some inevitable shortages. For example, the hole for displacing the embedded thermocouple damages the cutting edge strength, and the chip blocks the view contact between the tool tip and the thermal imager. This paper proposes two feed-forward multi-layered perceptron artificial neural network (ANN) models with Levenberg-Marquardt backpropagation training algorithms to determine the tool steady-state tip temperature for the dry turning process. The first model (called TC_ANN) calculates the steady-state tip temperature based on the temperatures of four specific points on the rake face. The second model (called TP_ANN) predicts the steady-state tip temperature via the cutting parameters. First, a fully thermo-mechanical finite element simulation model of the dry turning process is established. Next, the simulation model is repeated with different combinations of cutting parameters for sufficient times. Then, collection of the steady-state temperatures of the tool tip and these four specific points, and corresponding cutting parameters for each simulation model is conducted as the dataset to train these two ANN models. Based on the evaluation results with experimental data, the simulation model is validated to be reliable, and the mean relative errors of the tip temperature calculation for the actual turning process via TC_ANN and TP_ANN are 3.25% and 4.03%, respectively. Finally, the influences of cutting parameters on the tool tip temperature are investigated based on TP_ANN. It is found that the cutting speed and depth of cut have the most and least significant effects on the tip temperature, respectively, and the feed rate has almost the same influence as the depth of cut.

Prediction of noise emission in the machining of wood materials by means of an artificial neural network

Background: Noise produced during machining of wood materials can be a source of harm to workers and an environmental hazard. Understanding the factors that contribute to this noise will aid the development of mitigation strategies. In this study, an artificial neural network (ANN) model was developed to model the effects of wood species, cutting width, number of blades, and cutting depth on noise emission in the machining process. Methods: A custom application created with MATLAB codes was used for the development of the multilayer feed-forward ANN model. Model performance was evaluated by numerical indicators such as MAPE, RMSE, and R2. Results: The ANN model performed well with acceptable deviations. The MAPE, RMSE, and R2 values were 0.553%, 0.600, and 0.9824, respectively, in the testing phase. Furthermore, this study predicted the intermediate values not provided from the experimental study. The model predicted that lower noise emissions would occur with decreased cutting width and cutting depth. Conclusions: ANNs are quite effective in predicting the noise emission. Practitioners relying on the ANN approach for investigating the effects of various factors on noise emission can save time and costs by reducing the number of experimental combinations studied to generate predictive models.

Prediction of carbon sequestration of biochar produced from biomass pyrolysis by artificial neural network

Biochar has demonstrated its potential in carbon sequestration to mitigate climate change. The fact that biochar can be produced from the slow pyrolysis of numerous potential biomasses has also attracted attention. However, research on predicting the effect of different pyrolysis conditions and a wide variety of biomass on carbon sequestration potential of biochar is extremely limited. In order to estimate the feasibility and performance of biomass to produce biochar with good carbon sequestering potential, it is crucial to predict the quantity and surface property of the resulting biochar based on composition of different biomass and pyrolysis conditions. In this study, the optimum feedforward artificial neural network (FANN) models were developed for 3 analytical cases based on pyrolysis conditions, proximate and ultimate analysis of biomass feedstocks to predict yield and BET surface area of the resulting biochar. These aspects can reflect the carbon sequestration potential of the resulting biochar. Data collected from literature were used to train, validate and test the ANN model for all analytical cases in this study. Levenberg-Marquardt (LM) algorithm was found to be the most suitable training algorithm for each analytical case, as it had shown satisfactory performance with low mean absolute percentage error (MAPE), mean absolute error (MAE) and root mean square error (RMSE). The ANN models showed good performances with correlation coefficient (R) more than 0.96, coefficient of determination (R2) more than 0.92 and low MAPE, MAE and RMSE, thus indicating good alignment between the predicted and actual biochar yield and BET surface area. The relative importance of input was also determined using Garson’s equation and connection weight approach to investigate the impact of the input variables on biochar yield and BET surface area. The proximate analysis of biomass was found to have significant impact on biochar yield whereas ultimate analysis of biomass had large influence on biochar BET surface area.

Analysis and modeling of COVID-19 epidemic dynamics in Saudi Arabia using SIR-PSO and machine learning approaches.

COVID-19 has become a global concern because it has extensive damage to health, social and economic systems worldwide. Consequently, there is an urgent need to develop tools to understand, analyze, monitor and control further outbreaks of the disease. The Susceptible Infected Recovered-Particle SwarmOptimization model and the feed-forward artificial neural network model were separately developed to model COVID-19 dynamics based on daily time-series data reported by the Saudi authorities from March 2, 2020 to February 21, 2021. The collected data were divided into training and validation datasets. The effectiveness of the investigated models was evaluated by using various performance metrics. The Susceptible-Infected-Recovered-Particle-Swarm-Optimization model was found to well predict the cumulative infected and recovered cases and to optimally tune the contact rate and the characteristic duration of the illness. The feed-forward artificial neural network model was found to be efficient in modeling daily new and cumulative infections, recoveries and deaths. The forecasts provided by the investigated models had high coefficient of determination values of more than 0.97 and low mean absolute percentage errors (around 7% on average). Both the Susceptible-Infected-Recovered-Particle-Swarm-Optimization and feed-forward artificial neural network models were efficient in modeling COVID-19 dynamics in Saudi Arabia. The results produced by the models can help the Saudi health authorities to analyze the virus dynamics and prepare efficient measures to control any future occurrence of the epidemic.

Bioinspired modeling and biogeography-based optimization of electrocoagulation parameters for enhanced heavy metal removal

Electrocoagulation is an effective wastewater treatment process for the removal of heavy metals. This study focuses on deriving optimal conditions for removing heavy metals, viz. Lead (Pb), Cobalt (Co), and Manganese (Mn) from simulated wastewater by investigating removal efficiency and energy consumption of electrocoagulation process. Five operational parameters namely pH (2–10), current density (0.076–0.189 A/cm2), inter-electrode distance (3–7 cm), solution temperature (30–70 °C) and charging time (5–25 cm) have been analyzed. To improve the treatment of heavy metals, a novel coupled approach, namely Artificial neural network - non-dominated sorting Biogeography based optimization (ANN-NSBBO), has been proposed. Using the experimental data, a feed-forward backpropagation ANN model is used with removal efficiency and energy consumption as the outputs. Optimal values of operational parameters for maximum removal efficiency and minimum energy consumption were obtained using multi-objective NSBBO over the trained ANN model. True pareto fronts for Cobalt, Lead and Manganese were obtained after 100 iterations of the optimization algorithm. The maximum removal efficiency of 98.66% was obtained for Cobalt at the electrical energy consumption of 0.204 kWh. Minimum energy consumption for electrocoagulation of Lead (5.34 x 10−6 kWh) gave 82.48% removal efficiency. The maximum removal efficiency of Manganese (101.238%) was achieved at 7.64 pH, 0.084 A/cm2 current density, 3.188 cm inter-electrode distance, 47.49 °C solution temperature, 19.758 min charging time, and 0.145 kWh energy consumption. The non-dominated optimum tradeoff between removal efficiency and energy consumption provides clarity on operating conditions for the electrocoagulation process. The proposed approach of enhancing heavy metal treatment could assist municipalities, industries, and the scientific communities in achieving the United Nation's sustainable development goal of heavy metal remediation.

Stability of biochar derived from banana peel through pyrolysis as alternative source of nutrient in soil: feedforward neural network modelling study.

Biochar derived from banana peels can be used as an alternative nutrient in the soil that can promote crop growth while reducing fertiliser usage. Biochar stability has proportional relationship to biochar residence time in the soil and potassium is one of the vital nutrients needed for plant growth. This research aims at providing optimum pyrolysis operating conditions like temperature, residence time, and heating rate using banana peels as feedstock. An electrical tubular furnace was used to conduct the pyrolysis process to convert banana peels into biochar. The elemental compositions of biochar are potassium, oxygen (O), and carbon (C) content. The O:C ratio was used as the biochar stability indicator. Analysis of results showed that operating temperature has the most remarkable effect on biochar yield, biochar stability, and biochar's potassium content. In addition, a multilayer feedforward artificial neural network model was developed for the pyrolysis process. Eleven training algorithms were selected to model the multi-input multi-output neural network (MIMO). The most suitable training algorithm was identified through four performance criterions which are root mean square error (RMSE), mean absolute error (MSE), mean absolute percentage error (MAPE), and regression (R2). The results show that the Levenberg-Marquardt backpropagation training algorithm has the lowest error. From the chosen training algorithm, neural network was trained, and optimum operating parameters for banana peel were predicted at 490°C, 110min, and 11°C/min with a high yield of 47.78%, O/C ratio of 0.2393, and 14.04 wt. % of potassium.

Novel Method for Magnetic Flux Density Estimation in the Vicinity of Multi-Circuit Overhead Transmission Lines

In this paper, a novel method for the magnetic flux density estimation in the vicinity of multi-circuit overhead transmission lines is proposed. The proposed method is based on a fully connected feed-forward artificial neural network model that is trained to estimate the magnetic flux density vector components for a range of single-circuit overhead transmission lines. The proposed algorithm is able to simplify estimation process in instances when there are two or more geometrically identical circuits present in the multi-circuit overhead transmission line. In such instances, artificial neural network model is employed to estimate the magnetic flux density distribution over a considered lateral profile for only one of such circuits. The magnetic flux density estimates of the other geometrically identical circuits are derived from these results. The proposed methodology defines the resultant magnetic flux density for the multi-circuit overhead transmission line in terms of the contributions made by individual circuits. The application of the proposed magnetic flux density estimation method is demonstrated on several multi-circuit configurations of overhead transmission lines. The performance of the proposed method is compared with the Biot-Savart law based method calculation results as well as with field measurement results.

Shear Strength Determination in RC Beams Using ANN Trained with Tabu Search Training Algorithm

The shear failure of reinforced concrete (RC) beams is a critical issue and has attracted the attention of researchers. The specific challenges of shear failure are the numerous factors affecting shear strength, the nonlinear behavior, and the nonlinear relationship between affecting parameters and the concrete properties. This study tackles this challenge by employing Artificial Neural Network (ANN) models. Since, according to No Free Lunch theorem, the performance of optimization algorithms is problem-dependent, this paper aims to assess the feasibility of modeling the shear strength of RC beams using ANNs trained with the Tabu Search Training (TST) algorithm. To this end, 248 experimental results were collected from the literature, and a feed-forward ANN model was employed to predict the shear strength. To assess its feasibility, the ANNs were also modeled using the Particle Swarm Optimization, and Imperialist Competitive Algorithms. As a traditional technique, the multiple regression model was also employed. The shear design equations of ACI-318-2019 were also investigated and compared with Tabu Search Trained ANN model. The analysis of results suggests the superiority of Tabu Search Trained ANNs in comparison to other suggested models in literature and the ACI-318-2019 design code.

Vibro-Fluidized Bed Drying of Pumpkin Seeds: Assessment of Mathematical and Artificial Neural Network Models for Drying Kinetics

Pumpkin seeds were dried in a vibro-fluidized bed dryer (VFBD) at different temperatures at optimized vibration intensity of 4.26 and 4 m/s air velocity. The drying characteristics were mapped employing semiempirical models and Artificial Neural Network (ANN). Prediction of drying behavior of pumpkin seeds was done using semiempirical models, of which, one was preferred as it indicated the best statistical indicators. Two-term model showed the best fit of data with R2 − 0.999, and lowest χ2 − 1.03 × 10−4 and MSE 7.55 × 10−5. A feedforward backpropagation ANN model was trained by the Levenberg–Marquardt training algorithm using a TANSIGMOID activation function with 2-10-2 topology. Performance assessment of ANN showed better prediction of drying behavior with R2 = 0.9967 and MSE = 5.21 × 10−5 for moisture content, and R2 = 0.9963 and MSE = 2.42 × 10−5 for moisture ratio than mathematical models. In general, the prediction of drying kinetics and other drying parameters was more precise in the ANN technique as compared to semiempirical models. The diffusion coefficient, Biot number, and hm increased from 1.12 × 10−9 ± 3.62 × 10−10 to 1.98 × 10−9 ± 4.61 × 10−10 m2/s, 0.51 ± 0.01 to 0.60 ± 0.01, and 1.49 × 10−7 ± 4.89 × 10−8 to 3.10 × 10−7 ± 7.13 × 10−8 m/s, respectively, as temperature elevated from 40 to 60°C. Arrhenius’s equation was used to the obtain the activation energy of 32.71 ± 1.05 kJ/mol.

Prediction of residual stress fields after shot-peening of TRIP780 steel with second-order and artificial neural network models based on multi-impact finite element simulations

Shot-peening is a mechanical surface treatment widely employed to enhance the fatigue life of metallic components by generating compressive residual stress fields below the surface. These fields are mainly impacted by the selection of the process parameters. The aim of this work is to propose a hybrid approach to conduct two predictive models: second-order model and feed-forward artificial neural network model. For this purpose, a 3D multiple-impact finite element model coupled to a central composite design of experiments was employed. A parametric analysis was also conducted to investigate the effect of the shot diameter, the shot velocity, the coverage, and the impact angle on the induced residual stress profile within a TRIP780 steel. It was found that both models predict with good agreement, the residual stress profile as a function of the process parameters and can be used in shot-peening optimization due to their responsiveness.

Microscopic and data-driven modeling and operation of thermal atomic layer etching of aluminum oxide thin films

With increasing demands for microchips and increasing needs in the nano-scale semiconductor manufacturing industry, atomic layer etching (ALE) has been developing into a critical etching process. Unlike its counterpart in the film deposition domain, atomic layer deposition (ALD), which has been extensively studied, ALE has not been fully studied yet from a modeling and operation point of view. Therefore, this work develops microscopic models to characterize the thermal ALE process of aluminum oxide thin films with two precursors (hydrogen fluoride and trimethylaluminum). First, the reaction mechanisms for the two half-cycles for the thermal ALE process are established. Electronically predicted geometries of the Al2O3 structure with two precursors are optimized. Along with the optimized geometries, possible reaction pathways are proposed and calculated by density functional theory (DFT)-based electronic structure calculations. The proposed reaction paths and their kinetic parameters are used in a kinetic Monte Carlo (kMC) algorithm, which is capable of capturing the features of the thermal ALE of aluminum oxide. The kMC simulation provides an etch time for the given steady-state operating conditions, which are validated via comparison with available experimental results. Finally, data sets collected from the kMC simulation are used to train a feed-forward artificial neural network (FNN) model. The trained FNN model accurately predicts an etch time and dramatically reduces the computation time compared to the kMC simulation, thereby making it possible to carry out real-time, model-based operational parameter calculations. In addition, the trained FNN model can be used to establish a feasible range of operating conditions without demanding experimental work.

MODELLING THE PERFORMANCE OF A CAMEL MILK STORAGE STRUCTURE WITH EVAPORATIVE COOLING USING ARTIFICIAL NEURAL NETWORK

Storage and marketing of camel milk in arid lands of Kenya is hampered by lack of cold storage facilities. This problem can be alleviated by using storage structures incorporating evaporative cooling whose performance depends on climatic conditions. The objective of this work was to develop an artificial neural network (ANN) to predict cooled milk temperature and cooling efficiency of a locally fabricated cooler. Data were obtained from the cooler which was tested under various experimental conditions. Using some of the experimental data for training, a three-layer feed-forward ANN model based on back propagation Levenberg-Marquardt algorithm was developed using the Neural Network Toolbox for MATLAB®. The optimal model had a 4-4-2 structure with sigmoid transfer function in both layers. The inputs of the model were ambient dry bulb temperature, wet bulb temperature, wind speed and temperature of drip water, whereas the outputs were cooled milk temperature and cooling efficiency. The experimental data set (n=165) was randomly divided into training (75%) and testing (25%) sub-sets. The performance of the ANN predictions was evaluated by comparing the predicted and experimental results. The predictions agreed well with experimental values with mean squared error of 10.2, mean relative error of 4.02% and correlation coefficients in the range of 0.86-0.93. This study reveals that, as an alternative to conventional modelling techniques, the ANN approach can be used successfully for predicting the performance of locally fabricated camel milk storage structures incorporating evaporative cooling in arid pastoral areas of Kenya. The model can be used as a design tool to estimate the sizing and performance of future coolers, as it allows the prediction of the performance of hypothetical coolers designed without a need for time demanding experimentation. This can aid in up-scaling the technology.

The quest for GRACE 3.0: improving our beloved risk score with machine learning

Abstract Background Although widely recommended for risk assessment of patients with acute coronary syndrome (ACS), the Global Registry of Acute Coronary Events (GRACE) score famously lacks discriminative power. On the other hand, in-hospital serum hemoglobin levels (HG) have been shown to simultaneously forecast both thrombotic and hemorrhagic hazards. Purpose To ascertain the extent to which the incorporation of HG in the GRACE score is able to increase its predictive ability. Methods Retrospective single-center study encompassing ACS patients consecutively admitted to a Cardiac Intensive Care Unit. Inclusion criteria comprised the acquaintance of GRACE score, HG and vital status on a 6-month follow-up, which served as the outcome. 3 discriminative models were first created: (standard) GRACE score (model 1); GRACE score plus HG, by means of logistic regression (model 2); GRACE score plus HG, by means of multilayer perceptron (a class of feedforward artificial neural network) (model 3). Hereafter, if models 2 and/or 3 were to be found significantly more discriminative than model 1, a correction factor would be calculated, also allowing for the conception of the most predictive model possible (model 4). The discriminative ability was estimated by both the area under the receiver-operating characteristic curve (AUC), and the dyad sensitivity/specificity. Results Between April 2009 and December 2016, 1468 patients met study inclusion criteria. Mean age was 68.0±13.2 years and 29.8% were female, while 36.9% presented with ST-segment elevation myocardial infarction. Mean GRACE score was 145.5±47.0 and mean HG was 13.5±2.0. All-cause mortality reached 10.5%, at 6 months. Predictive power for models 1, 2 and 3 may be quantified as follows: AUC 0.6998, sensitivity 77.7% and specificity 62.5%; AUC 0.7818, sensitivity 36.3% and specificity 92.2%; AUC 0.7851, sensitivity 47.7% and specificity 88.5%, respectively. Both models 2 and 3 exhibited more discriminative ability than model 1 (p<0.001), due to their higher specificity. As such, a correction factor was computed (y = −7.8556x + 86.4117) and model 4 was created, displaying a sensitivity of 65.9% and a specificity of 76.5%. Conclusion HG single-handedly provides incremental predictive value – namely more specificity – to the GRACE score. In particular, the latter seems to overestimate ACS patients' risk if HG is normal or close to normal. Funding Acknowledgement Type of funding sources: None.

Prediction of storage time in different seafood based on color values with artificial neural network modeling.

The determination of storage time in seafood could be performed by microbiological, chemical and sensory analysis. Among these mentioned methods color changes are one part of sensory analysis and are prior acceptance criteria from the point of consumers' view. In this study, a feedforward artificial neural network (ANN) model was developed to predict the storage time of seafood based on L*, a* and b* values. A total of 205 data set were compiled from the literature that represents the color changes of different seafood products to train and test the ANN model. Another set of data (n = 45) were used for the validation of developed ANN model. A multi-layer perceptron (MLP) was applied for the determination of agreements between input and output data. The most accurate topology were determined in accordance with the changes in the values of correlation coefficients (R2) and mean square errors (MSE) and found to be 30 neurons in the layer (R2 = 0.81 and MSE = 0.2). The performance of ANN model was evaluated based on 6 criteria such as Mean Absolute Deviation (MAD), Mean Square Errors (MSE), Residual Mean Square Errors (RMSE), Correlation Coefficient (R2), Mean Absolute Error (MAE) and F-test statistics and found to be 0.2, 0.05, 0.002, 0.8, 0.71 and 1.06, respectively. Moreover, predicted and observed storage time values were fitted and regression coefficient was found to be 0.85. In accordance with the results of this study, the proposed ANN model is accurate, reliable, and proper for the estimation of storage time in seafood products.

Modelling of adsorption of anionic azo dye using Strychnos potatorum Linn seeds (SPS) from aqueous solution with artificial neural network (ANN)

Synthetic dyes used in the textile and paper industries pose a major threat to the environment. In the present research work, the adsorption efficiency of the natural adsorbent Strychnos potatorum Linn (Fam: Loganiaceae) seeds were examined against the reactive orange-M2R dye from aqueous solution by varying the process conditions such as contact time, pH, adsorbent dosage, and initial dye concentration on adsorption of anionic azo dye. This study compares different types of artificial neural networks which are feedforward artificial neural network (FANN) and nonlinear autoregressive exogenous (NARX) model to predict the efficiency of a cost-effective natural adsorbent Strychnos potatorum Linn seeds on removing reactive orange-M2R dye from aqueous solution. Twelve training algorithms of neural network were compared, and the prediction on the adsorption performance of anionic azo dye from aqueous solution using Strychnos potatonum Linn seeds was evaluated by using the root mean squared error (RMSE), mean absolute error (MAE), coefficient of determination (R2), and accuracy. For FANN model, Levenberg-Marquardt (LM) backpropagation with 19 hidden neurons was selected as the optimum FANN model, with R2 of 0.994 and accuracy of 87.20%, 98.21%, and 66.60% for training, testing, and validation datasets, respectively. For NARX model, LM with 8 hidden neurons was selected as the most suitable training algorithm, with R2 value of more than 0.99 and accuracy of 88.00%, 90.91%, and 75.00% for training, testing, and validation datasets, respectively. NARX model accurately predicted the adsorption of anionic azo dye from aqueous solution using Strychnos potatonum Linn seeds with better performance than FANN model.