Two trials were conducted under Mediterranean conditions to monitor several physiological indicators before harvest (leaf chlorophyll concentration, quantum yield of photosystem II electron transport, stem water potential, and stomatal conductance) and some agronomic performance parameters before and at harvest (vigor, fruit growth, fruit size, fruit weight, and yield), of ‘Vairo’ almond and ‘Big Top’ nectarine cultivars grafted onto eight Prunus rootstocks, six of which are common in both cultivars. For both ‘Vairo’ almond and ‘Big Top’ nectarine cultivars, factors including rootstock, date, and the interaction between rootstock and date, from fruit set to harvest were evaluated. Significantly affected were certain physiological and agronomical traits which were evaluated before harvest, with stem water potential being the parameter affected by interaction in both cultivars. In fact, the stem water potential presented low levels in Rootpac-20 and high levels in Rootpac-40 for both cultivars. With regard to the other physiological traits evaluated during the growing period, changes in stomatal conductance were observed in ‘Vairo’, but not in ‘Big Top’. Comparing rootstocks throughout the season, Rootpac-40 and IRTA-1 exhibited the highest stomatal conductance values, whereas the lowest was observed in Rootpac-R; Rootpac-20 and Ishtara also presented low values. Regarding agronomical traits at harvest, GF-677 and IRTA-1 produced high yields for ‘Vairo’ almond cultivar, whereas Rootpac-40 and Ishtara performed better with ‘Big Top’ nectarine cultivar.
Given the hyper-spectral imaging unique potentials in grasping the polymer characteristics of different materials, it is commonly used in sorting procedures. In a practical plastic sorting scenario, multiple plastic flakes may overlap which depending on their characteristics, the overlap can be reflected in their spectral signature. In this work, we use hyper-spectral imaging for the segmentation of three types of plastic flakes and their possible overlapping combinations. We propose an intuitive and simple multi-label encoding approach, bitfield encoding, to account for the overlapping regions. With our experiments, we show that the bitfield encoding improves over the baseline single-label approach and we further demonstrate its potential in predicting multiple labels for overlapping classes even when the model is only trained with non-overlapping classes.
Given the hyper-spectral imaging unique potentials in grasping the polymer characteristics of different materials, it is commonly used in sorting procedures. In a practical plastic sorting scenario, multiple plastic flakes may overlap which depending on their characteristics, the overlap can be reflected in their spectral signature. In this work, we use hyper-spectral imaging for the segmentation of three types of plastic flakes and their possible overlapping combinations. We propose an intuitive and simple multi-label encoding approach, bitfield encoding, to account for the overlapping regions. With our experiments, we show that the bitfield encoding improves over the baseline single-label approach and we further demonstrate its potential in predicting multiple labels for overlapping classes even when the model is only trained with non-overlapping classes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.