Ultrasound processing of fruits and vegetables,structural modification and impact on nutrient and bioactive compounds: a review

This review presents an updated analysis regarding the application of ultrasound technology in fruits, vegetables and their derivatives. The relationship among structure, processing, the quantity and quality of nutrients and bioactive compounds are discussed. Initially, we discussed the effect of ultrasound processing on the structure of the matrices at tissues, cells and molecules levels, also considering the different factors that influence the reported responses. Subsequently, the effect on nutrients and bioactive compound quantity (concentration) and quality (bioaccessibility → bioavailability → bioactivity) is evaluated. Ultrasound processing resulting in tissues and cell disruption, fibre breakage, isomerisation, micellisation, among other modifications, improving the extractability of compounds and/or resulting in their degradation. Moreover, the obtained new matrix interacts differently with the human body, affecting the compound accessibility, which can be increased. In conclusion, different possibilities are discussed regarding using ultrasound processing to enhance healthy aspects of plant-based food products.     

A Compute Cache System for Signal Processing Applications

Journal of Signal Processing Systems - Nowadays, processing systems are constrained by the low efficiency of their memory subsystems. Although memories evolved into faster and more efficient...     

Deep learning and multivariate time series for cheat detection in video games

Machine Learning - Online video games drive a multi-billion dollar industry dedicated to maintaining a competitive and enjoyable experience for players. Traditional cheat detection systems struggle...     

Self-attention generative adversarial networks applied to conditional music generation

The task of audio and music generation in the waveform domain has become possible due to recent advances in deep learning. Generative Adversarial Networks (GANs) are a type of generative model that has achieved success in areas such as image, video and audio generation. However, realistic audio generation with GANs is still a challenge, thanks to the specific characteristics inherent to this kind of data. In this paper we propose a GAN model that employs the self-attention mechanism and produces small chunks of music conditioned by instrument. We compare our model to a baseline and run ablation studies in order to demonstrate its superiority. We also suggest some applications of the model, particularly in the area of computer assisted composition.

     

Visual monitoring of High-Sea fishing activities using deep learning-based image processing

Multimedia Tools and Applications - Due to the increasing shortage of fish in the seas, Vessel Monitoring Systems (VMS) play a very important role in fishing activity monitoring, control and...