Comparison of ultrasound-assisted extraction with conventional extraction methods of oil and polyphenols from grape (Vitis vinifera L.) seeds

Ultrasound-assisted extraction (US) carried out at 20 KHz, 150 W for 30 min gave grape seed oil yield (14% w/w) similar to Soxhlet extraction (S) for 6 h. No significant differences for the major fatty acids was observed in oils extracted by S and US at 150 W. Instead, K₂₃₂ and K₂₆₈ of US- oils resulted lower than S-oil. From grape seeds differently defatted (S and US), polyphenols and their fractions were extracted by maceration for 12 h and by ultrasound-assisted extraction for 15 min. Sonication time was optimized after kinetics study on polyphenols extraction. Grape seed extracts obtained from seeds defatted by ultrasound (US) and then extracted by maceration resulted the highest in polyphenol concentration (105.20 mg GAE/g flour) and antioxidant activity (109 Eq αToc/g flour).     

Efficient identification of independence networks using mutual information

Conditional independence graphs are now widely applied in science and industry to display interactions between large numbers of variables. However, the computational load of structure identification grows with the number of nodes in the network and the sample size. A tailored version of the PC algorithm is proposed which is based on mutual information tests with a specified testing order, combined with false negative reduction and false positive control. It is found to be competitive with current structure identification methodologies for both estimation accuracy and computational speed and outperforms these in large scale scenarios. The methodology is also shown to approximate dense networks. The comparisons are made on standard benchmarking data sets and an anonymized large scale real life example.     

Occlusion-Based Explanations in Deep Recurrent Models for Biomedical Signals

The biomedical field is characterized by an ever-increasing production of sequential data, which often come in the form of biosignals capturing the time-evolution of physiological processes, such as blood pressure and brain activity. This has motivated a large body of research dealing with the development of machine learning techniques for the predictive analysis of such biosignals. Unfortunately, in high-stakes decision making, such as clinical diagnosis, the opacity of machine learning models becomes a crucial aspect to be addressed in order to increase the trust and adoption of AI technology. In this paper, we propose a model agnostic explanation method, based on occlusion, that enables the learning of the input’s influence on the model predictions. We specifically target problems involving the predictive analysis of time-series data and the models that are typically used to deal with data of such nature, i.e., recurrent neural networks. Our approach is able to provide two different kinds of explanations: one suitable for technical experts, who need to verify the quality and correctness of machine learning models, and one suited to physicians, who need to understand the rationale underlying the prediction to make aware decisions. A wide experimentation on different physiological data demonstrates the effectiveness of our approach both in classification and regression tasks.     

Ultrasound-assisted extraction coupled with under vacuum distillation of flavour compounds from spearmint (carvone-rich) plants: Comparison with conventional hydrodistillation

Ultrasonically assisted extraction of flavour compounds from different varieties of Mentha spicata, using 70% ethanol, have been carried out for 5, 10 and 15 min and coupled with under vacuum distillation. The ultrasound distilled extracts have been analysed by GC–MS and compared with essential oils obtained by hydrodistillation. The results have showed that ultrasonically assisted extraction in combination with under vacuum distillation have provided extracts with higher flavouring strength due to the increased concentration of desirable oxygenated compounds (from 5 to 8 times) compared with hydrodistillation. Extraction yields of flavour volatiles have been calculated giving a range 0.04–0.13% by ultrasound and 0.01–0.02% by hydrodistillation.