Robotic weed control has seen increased research of late with its potential for boosting productivity in agriculture. Majority of works focus on developing robotics for croplands, ignoring the weed management problems facing rangeland stock farmers. Perhaps the greatest obstacle to widespread uptake of robotic weed control is the robust classification of weed species in their natural environment. The unparalleled successes of deep learning make it an ideal candidate for recognising various weed species in the complex rangeland environment. This work contributes the first large, public, multiclass image dataset of weed species from the Australian rangelands; allowing for the development of robust classification methods to make robotic weed control viable. The DeepWeeds dataset consists of 17,509 labelled images of eight nationally significant weed species native to eight locations across northern Australia. This paper presents a baseline for classification performance on the dataset using the benchmark deep learning models, Inception-v3 and ResNet-50. These models achieved an average classification accuracy of 95.1% and 95.7%, respectively. We also demonstrate real time performance of the ResNet-50 architecture, with an average inference time of 53.4 ms per image. These strong results bode well for future field implementation of robotic weed control methods in the Australian rangelands.
Mushrooms and mushroom extracts have traditionally been used as therapies for a wide variety of ailments, including allergy, arthritis, and other inflammatory disorders. However, more evidence is required on the mechanism by which mushrooms exert these effects. In the present study, the anti-inflammatory properties of ethanol and hot water extracts prepared from 27 fungal samples collected between October and November 2011 at various forest locations in the southwest of Ireland were investigated using the lipopolysaccharide (LPS)-stimulated mouse macrophage (RAW264.7 cells) model of inflammation. LPS-stimulated cells were incubated in the presence of mushroom extracts at nontoxic concentrations for 24 h and the production of interleukin-6 (IL-6) was quantified by ELISA. Seven ethanolic and one hot water extract that decreased IL-6 production were selected for further study. The extracts were then incubated with LPS-stimulated cells for 24 h and the production of IL-6, tumor necrosis factor-alpha (TNF-α), and nitric oxide (NO) was measured. Ethanolic extracts prepared from Russula mairei, Lactarius blennius, Craterellus tubaeformis, Russula fellea, and Craterellus cornucopioides demonstrated selective anti-inflammatory activity by decreasing the production of NO and IL-6 but not TNF-α in LPS-stimulated RAW264.7 cells. These findings support existing evidence of the anti-inflammatory potential of mushroom extracts.
In this paper, we present a new class of representations of signals in the time-frequency (TF) plane. These representations are complex valued, linear, and satisfy reconstruction conditions in which the signal and its complex spectrum may be uniquely reconstructed from their TF representation. These surfaces are generalizations of one-dimensional linear transforms with which they share many properties. The primary advantage of these representations is that the phase of the surface may be used to recover signal information which is not contained in real TF surfaces. Linearity guarantees that cross-terms normally associated with TF distributions do not exist in these representations. Several examples of invertible surfaces are presented, and it is demonstrated that these surfaces agree with normal intuition. Finally, a method, based on the phase gradient, is proposed as a method of modifying Fourier surfaces to produce representations which are more focused or more concentrated in time and frequency.
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.
customersupport@researchsolutions.com
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.