Transfer learning between crop types for semantic segmentation of crops versus weeds in precision agriculture

Agricultural robots rely on semantic segmentation for distinguishing between crops and weeds to perform selective treatments and increase yield and crop health while reducing the amount of chemicals used. Deep‐learning approaches have recently achieved both excellent classification performance and real‐time execution. However, these techniques also rely on a large amount of training data, requiring a substantial labeling effort, both of which are scarce in precision agriculture. Additional design efforts are required to achieve commercially viable performance levels under varying environmental conditions and crop growth stages. In this paper, we explore the role of knowledge transfer between deep‐learning‐based classifiers for different crop types, with the goal of reducing the retraining time and labeling efforts required for a new crop. We examine the classification performance on three datasets with different crop types and containing a variety of weeds and compare the performance and retraining efforts required when using data labeled at pixel level with partially labeled data obtained through a less time‐consuming procedure of annotating the segmentation output. We show that transfer learning between different crop types is possible and reduces training times for up to 80%. Furthermore, we show that even when the data used for retraining are imperfectly annotated, the classification performance is within 2% of that of networks trained with laboriously annotated pixel‐precision data.     

Bacteriophages vB_Sen-TO17 and vB_Sen-E22, Newly Isolated Viruses from Chicken Feces,Specific for Several Salmonella enterica Strains

Two newly discovered bacteriophages, isolated from chicken feces and infecting Salmonella enterica strains, are described in this report. These phages have been named vB_Sen-TO17 and vB_Sen-E22, and we present their molecular and functional characterization. Both studied viruses are able to infect several S. enterica strains and develop lytically, but their specific host ranges differ significantly. Electron microscopic analyses of virions have been performed, and full genome sequences were determined and characterized, along with molecular phylogenetic studies. Genomes of vB_Sen-TO17 (ds DNA of 41,658 bp) and vB_Sen-E22 (dsDNA of 108,987 bp) are devoid of homologs of any known or putative gene coding for toxins or any other proteins potentially deleterious for eukaryotic cells. Both phages adsorbed efficiently (>95% adsorbed virions) within 10 min at 42 °C (resembling chicken body temperature) on cells of most tested host strains. Kinetics of lytic development of vB_Sen-TO17 and vB_Sen-E22, determined in one-step growth experiments, indicated that development is complete within 30–40 min at 42 °C, whereas burst sizes vary from 9 to 79 progeny phages per cell for vB_Sen-TO17 and from 18 to 64 for vB_Sen-E22, depending on the host strain. Virions of both phages were relatively stable (from several percent to almost 100% survivability) under various conditions, including acidic and alkaline pH values (from 3 to 12), temperatures from −80 °C to 60 °C, 70% ethanol, chloroform, and 10% DMSO. These characteristics of vB_Sen-TO17 and vB_Sen-E22 indicate that these phages might be considered in further studies on phage therapy, particularly in attempts to eliminate S. enterica from chicken intestine.     

The Mechanical Properties of the Novel Nanocrystalline Refractory Tantalum Alloys

Protection of Metals and Physical Chemistry of Surfaces - The nanocrystalline tantalum alloys were investigated in terms of mechanical properties. The materials were obtained by powder metallurgy...     

Magnetic Resonance Signal Amplification by Reversible Exchange of Selective PyFALGEA Oligopeptide Ligands Towards Epidermal Growth Factor Receptors

The biorelevant PyFALGEA oligopeptide ligand, which is selective towards the epidermal growth factor receptor (EGFR), has been successfully employed as a substrate in magnetic resonance signal amplification by reversible exchange (SABRE) experiments. It is demonstrated that PyFALGEA and the iridium catalyst IMes form a PyFALGEA:IMes molecular complex. The interaction between PyFALGEA:IMes and H₂ results in a ternary SABRE complex. Selective 1D EXSY experiments reveal that this complex is labile, which is an essential condition for successful hyperpolarization by SABRE. Polarization transfer from parahydrogen to PyFALGEA is observed leading to significant enhancement of the ¹H NMR signals of PyFALGEA. Different iridium catalysts and peptides are inspected to discuss the influence of their molecular structures on the efficiency of hyperpolarization. It is observed that PyFALGEA oligopeptide hyperpolarization is more efficient when an iridium catalyst with a sterically less demanding NHC ligand system such as IMesBn is employed. Experiments with shorter analogues of PyFALGEA, that is, PyLGEA and PyEA, show that the bulky phenylalanine from the PyFALGEA oligopeptide causes steric hindrance in the SABRE complex, which hampers hyperpolarization with IMes. Finally, a single-scan ¹H NMR SABRE experiment of PyFALGEA with IMesBn revealed a unique pattern of NMR lines in the hydride region, which can be treated as a fingerprint of this important oligopeptide.     

Gas‐phase removal of indoor volatile organic compounds and airborne microorganisms over mono‐ and bimetal‐modified (Pt,Cu, Ag) titanium(IV) oxide nanocomposites

The photocatalytic deactivation of volatile organic compounds and mold fungi using TiO₂ modified with mono‐ and bimetallic (Pt, Cu, Ag) particles is reported in this study. The mono‐ and bimetal‐modified (Pt, Cu, Ag) titanium(IV) oxide photocatalysts were prepared by chemical reduction method and characterized using XRD, XPS, DR/UV‐Vis, BET, and TEM analysis. The effect of incident light, type and content of mono‐ and bimetallic nanoparticles deposited on titanium(IV) oxide was studied. Photocatalytic activity of as‐prepared nanocomposites was examined in the gas phase using LEDs array. High photocatalytic activity of Ag/Pt‐TiO₂ and Cu/Pt‐TiO₂ in the reaction of toluene degradation resulted from improved efficiency of interfacial charge transfer process, which was consistent with the fluorescence quenching effect revealed by photoluminescence (PL) emission spectra. The photocatalytic deactivation of Penicillium chrysogenum, a pathogenic fungi present in the indoor environment, especially in a damp or water‐damaged building using mono‐ and bimetal‐modified (Pt, Cu, Ag) titanium(IV) oxide was evaluated for the first time. TiO₂ modified with mono‐ and bimetallic NPs of Ag/Pt, Cu, and Ag deposited on TiO₂ exhibited improved fungicidal activity under LEDs illumination than pure TiO₂.     

Participatory design of a robot for demonstrating an epileptic seizure

ABSTRACT

We present the methodology and results of participatory design of a robot for presenting an epileptic seizure and a scenario of the educational workshop using this robot. Children with epilepsy encounter stigma and stereotypes and may receive inadequate aid when having an epileptic seizure. The goal of the larger project was to use the prototype device in a series of workshops for improving teachers' actions during an epileptic seizure and their attitudes towards epileptic students. In this paper, we show how various design goals for an educational robot were accomplished to fit the needs of all identified stakeholders, particularly people with epilepsy.

We used a co-design (participatory design) approach through a series of meetings participated by members of the association Polish Association for People Suffering from Epilepsy, students and faculty members of the biomedical engineering and robotics departments, teachers, psychologists and medical specialists (epileptologist, neurologist).

These meetings created an opportunity for a better understanding of the (functional and nonfunctional) requirements and resulting tradeoffs and led the participants to find appropriate solutions. Participation of people with epilepsy in the design process allowed them to deal with the potentially stereotyped representation of themselves. The prototype robot, therefore, combined goals of various stakeholders, such as an accurate presentation of an epileptic seizure, lightweight, ease of use and control, while preserving the dignity of people with epilepsy.

As a result of the co-designing process, an inexpensive robot was created and used in a series of 10 pilot workshops with 217 participants, mainly teachers of primary and middle schools. Teachers improved their understanding of epilepsy and suggested further improvements to the system.     

Microstructural characterization of plasma sprayed Ln2Zr2O7 thermal barrier coatings by electron microscopy methods

The presented article characterized microstructural aspects of thermal barrier coatings (TBCs) analysis using methods of electron microscopy such as electron backscatter diffraction (EBSD), transmission/scanning electron microscopy (S/TEM), and TEM. The analyzed TBC system is based on gadolinium zirconate deposited by air plasma spraying method, and additionally, it was subjected to an oxidation test for 500 hr at a temperature of 1,100°C. Moreover, the morphological characterization of feedstock powder was showed. EBSD analysis revealed the inhomogeneity of feedstock materials in the form of complex phase composition. In the case of deposited coating, this method was used to characterize the crystallite size of zirconate coating and phase composition of thermally grown oxide zone. S/TEM and TEM analysis showed morphological details of this zone but not revealed such phase as perovskite oxide of GdAlO₃ type.     

A three-dimensional heterogeneity analysis of electrochemical energy conversion in SOFC anodes using electron nanotomography and mathematical modeling

In this paper a fully three dimensional, multiphase, micro-scale solid oxide fuel cell anode transport phenomena numerical model is proposed and verified. The Butler-Volmer model was combined with empirical relations for conductivity and diffusivity - notably the Fuller-Shetler-Giddings equation, and the Fickian model for transport of gas reagents. FIB-SEM tomography of a commercial SOFC stack anode was performed and the resulting images were processed to acquire input data. A novel method for estimating local values of Triple Phase Boundary length density for use in a three-phase, three-dimensional numerical mesh was proposed. The model equations are solved using an in-house code and the results were verified by comparison to an analytical solution within the range of its applicability. A limited parametric study was performed to qualitatively assess simulation performance and impact of heterogeneity. Despite the high dependence of the SOFC anode performance on the geometry of its anisotropic, three-phase microstructure there are very few micro-scale numerical models simulating transport phenomena within these electrodes.