Classification of Bitter Orange Essential Oils According to Fruit Ripening Stage by Untargeted Chemical Profiling and Machine Learning.

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.

Evaluating the potential of artificial neural network and neuro-fuzzy techniques for estimating antioxidant activity and anthocyanin content of sweet cherry during ripening by using image processing.

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.