Search

In this study, two widely used artificial intelligence techniques, i.e. Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS), were applied for global solar radiation (GSR) prediction in Isfahan Province, Iran. Different sets of meteorological data were used as inputs to specify the best set of inputs. Relative humidity and precipitation had an unfavorable effect on radiation prediction, while the number of days, sunshine duration, minimum temperature, maximum temperature, daylight hours and clear-sky radiation were effective parameters to determine GSR. Using the mentioned parameters as inputs, 6-5-1 architecture had the best performance without overtraining. In ANFIS models, ' triangular-shaped' had the highest performance amongst different types of membership functions. Resulted correlation coefficients and errors showed that ANN was generally better than ANFIS for this purpose. [ABSTRACT FROM AUTHOR]

Among the different classes of physical properties of foods, color is considered the most important visual attribute in quality perception. Consumers tend to associate color with quality due to its good correlation with physical, chemical and sensorial evaluations of food quality. This study used an inexpensive method to predict sweet cherries color parameters by combining image processing and artificial neural network (ANN) techniques. The color measuring technique consisted of a CCD camera for image acquisition, MATLAB software for image analysis, and ANN for modeling. To demonstrate the usefulness of this technique, changes of cherry color during ripening were studied. After designing, training, and generalizing several ANNs using Levenberg- Marquardt algorithm, a network with 7-14-11-3 architecture showed the best correlation (R2= 0.9999) for L*, a* and b* values from Chroma meter and the machine vision system. L* and b* parameters decreased during ripening of cherries and a* parameter increased at first and then decreased. Evaluation of L*, a* and b* values showed the possibility of reliable use of this system for determination of absolute color values of foodstuffs with a much lower cost in comparison with Chroma meter. [ABSTRACT FROM AUTHOR]

The quality and composition of bitter orange essential oils (EOs) strongly depend on the ripening stage of the citrus fruit. The concentration of volatile compounds and consequently its organoleptic perception varies. While this can be detected by trained humans, we propose an objective approach for assessing the bitter orange from the volatile composition of their EO. The method is based on the combined use of headspace gas chromatography⁻mass spectrometry (HS-GC-MS) and artificial neural networks (ANN) for predictive modeling. Data obtained from the analysis of HS-GC-MS were preprocessed to select relevant peaks in the total ion chromatogram as input features for ANN. Results showed that key volatile compounds have enough predictive power to accurately classify the EO, according to their ripening stage for different applications. A sensitivity analysis detected the key compounds to identify the ripening stage. This study provides a novel strategy for the quality control of bitter orange EO without subjective methods.

Background: This paper presents a versatile way for estimating antioxidant activity and anthocyanin content at different ripening stages of sweet cherry by combining image processing and two artificial intelligence (AI) techniques. In comparison with common time-consuming laboratory methods for determining these important attributes, this new way is economical and much faster. The accuracy of artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) models was studied to estimate the outputs. Sensitivity analysis and principal component analysis were used with ANN and ANFIS respectively to specify the most effective attributes on outputs., Results: Among the designed ANNs, two hidden layer networks with 11-14-9-1 and 11-6-20-1 architectures had the highest correlation coefficients and lowest error values for modeling antioxidant activity (R = 0.93) and anthocyanin content (R = 0.98) respectively. ANFIS models with triangular and two-term Gaussian membership functions gave the best results for antioxidant activity (R = 0.87) and anthocyanin content (R = 0.90) respectively., Conclusion: Comparison of the models showed that ANN outperformed ANFIS for this case. By considering the advantages of the applied system and the accuracy obtained in somewhat similar studies, it can be concluded that both techniques presented here have good potential to be used as estimators of proposed attributes., (© 2013 Society of Chemical Industry.)