Search

The field of computer vision has shown great potential for the identification of crops at large scales based on multispectral images. However, the challenge in designing crop identification networks lies in striking a balance between accuracy and a lightweight framework. Furthermore, there is a lack of accurate recognition methods for non-large-scale crops. In this paper, we propose an improved encoder-decoder framework based on DeepLab v3+ to accurately identify crops with different planting patterns. The network employs ShuffleNet v2 as the backbone to extract features at multiple levels. The decoder module integrates a convolutional block attention mechanism that combines both channel and spatial attention mechanisms to fuse attention features across the channel and spatial dimensions. We establish two datasets, DS1 and DS2, where DS1 is obtained from areas with large-scale crop planting, and DS2 is obtained from areas with scattered crop planting. On DS1, the improved network achieves a mean intersection over union (mIoU) of 0.972, overall accuracy (OA) of 0.981, and recall of 0.980, indicating a significant improvement of 7.0%, 5.0%, and 5.7%, respectively, compared to the original DeepLab v3+. On DS2, the improved network improves the mIoU, OA, and recall by 5.4%, 3.9%, and 4.4%, respectively. Notably, the number of parameters and giga floating-point operations (GFLOPs) required by the proposed Deep-agriNet is significantly smaller than that of DeepLab v3+ and other classic networks. Our findings demonstrate that Deep-agriNet performs better in identifying crops with different planting scales, and can serve as an effective tool for crop identification in various regions and countries.

Objectives: Investigate the biomechanical characteristics in tracheostomized patients with aspiration following acquired brain injury (ABI) and further explore the relationship between the biomechanical characteristics and aspiration. Methods: This is a single-center cross-sectional study. The tracheostomized patients with aspiration following ABI and age-matched healthy controls were recruited. The biomechanical characteristics, including velopharynx (VP) maximal pressure, tongue base (TB) maximal pressure, upper esophageal sphincter (UES) residual pressure, UES relaxation duration, and subglottic pressure, were examined by high-resolution manometry and computational fluid dynamics simulation analysis. The penetration–aspiration scale (PAS) score was evaluated by a videofluoroscopic swallowing study. Results: Fifteen healthy subjects and fifteen tracheostomized patients with aspiration following ABI were included. The decreased VP maximal pressure, increased UES residual pressure, and shortened UES relaxation duration were found in the patient group compared with the control group (p < 0.05). Furthermore, the subglottic pressure significantly decreased in patients (p < 0.05), while no significant difference was found in TB maximal pressure between groups (p > 0.05). In addition, in the patient group, VP maximal pressure (rs = −0.439; p = 0.015), UES relaxation duration (rs = −0.532; p = 0.002), and the subglottic pressure (rs = −0.775; p < 0.001) were negatively correlated with the PAS score, while UES residual pressure (rs = 0.807; p < 0.001) was positively correlated with the PAS score (p < 0.05), the correlation between TB maximal pressure and PAS score (rs = −0.315; p = 0.090) did not reach statistical significance. Conclusions: The biomechanical characteristics in tracheostomized patients with aspiration following ABI might manifest as decreased VP maximal pressure and subglottic pressure, increased UES residual pressure, and shortened UES relaxation duration, in which VP maximal pressure, UES relaxation duration, subglottic pressure, and UES residual pressure were correlated with aspiration.

In the theory of traditional Chinese medicine, acupoints refer to special points and areas on the meridian line of the human body. Traditional Chinese medicine believes that the application of unique techniques such as pressing, kneading, rubbing, pushing, and patting to acupoints or massage with the help of specific tools has the effects of promoting blood circulation, dredging meridians, and eliminating fatigue. At present, most automatic massage devices are for large-area massage of the trunk, and few are specifically for acupoint massage of the limbs. First, this paper analyzes the characteristics of traditional Chinese medical acupoint massage and then obtains the design index of an automatic acupoint massage device. After that, based on the principle of a series elastic actuating mechanism, a flexible uni-acupoint massage device and control system, imitating the acupoint massage technique of traditional Chinese medicine, were designed. In order to analyze the massage force of the massage device, the man–machine contact dynamic model of the massage device was established, and the force of the massage device was simulated and analyzed. Finally, an experimental platform was built to verify the massage force and massage process of the massage device. The experimental results show that the massage device designed in this paper meets the indexes of traditional Chinese medical massage, in terms of the massage process and massage force, and verify the rationality of the design.

Background: Integrating multi-omics data for cancer subtype recognition is an important task in bioinformatics. Recently, deep learning has applied to recognize the subtype of cancers. However, existing studies almost integrate the multi-omics data simply by concatenation as the single data and then learn a latent low-dimensional representation through deep learning model, which didn't considering the distributes differently of omics data. Moreover, these methods ignore the relationship of samples. Results :In order to tackle these problems, we proposed SADLN: a self-attention based deep learning network of integrating multi-omics data for cancer subtype recognition. SADLN combined encoder, self-attention, decoder, and discriminator into a unified framework, which can not only integrate multi-omics data but also adaptively model the sample’s relationship for learning a accurately latent low-dimensional representation. With the integrated representation learned from the network, SADLN used Gaussian Mixture Model to identify cancer subtypes. Experiments on ten cancer datasets of TCGA demonstrated the advantages of SADLN compared to ten methods. Conclusions: The Self-Attention Based Deep Learning Network (SADLN) is a effective method of integrate multi-omics data for cancer subtype recognition.

To balance the paradox of both high mechanical properties and electrical conductivity of copper alloys, a nominal hot-rolled Cu-0.4 wt.%Cr-0.3 wt.%Zr alloy strips were subjected to different thermo-mechanical process. The microstructures of the alloys are characterized by optical microscopy and transmission electron microscopy and the mechanical properties and the electrical conductivity are evaluated. The results show that a desired combination of strength, ductility and conductivity can be obtained by controlling the sequence of cold rolling and aging. It suggests that the treatment route with an order of aging followed by cold rolling (ACR) is better than that with the order of cold rolling with aging (CRA). The ultimate tensile strength 568 MPa and electrical conductivity 75.3%IACS are obtained after aging at 450 °C for 3 h followed by 80% cold rolling at room temperature. The high electrical conductivity and ductility is attributed to twin lamellar structure.

Additional file 1: Scheme S1. The synthetic route of tLyP-1-PEI-PLGA. Figure S1. Mass spectrum of tLyP-1(CGNKRTR). Figure S2. NMR spectrum of tLyP-1, PEI, and tLyP-1-PEI. Figure S3. HPLC result of tLyP-1 before (upper) and after (lower) conjugating to PEI. Figure S4. TOF-MS spectrum of PLGA: calcd. 14955.22 and tLyP-1-PEI-PLGA: calcd. 20722.68. Figure S5. Fluorescence image of DiI-labeled TPP@PTX-CuTCPP, the scale bar is 20 μm (inset: optical image of TPP@PTX-CuTCPP, the scale bar is 20 μm). Figure S6. Size distribution of TPP@PTX-CuTCPP dispersed in various media including deionized water, PBS buffer, and 1640 containing fetal bovine serum (FBS). Figure S7. Digital photography of NPs before (left) and after (right) encapsulation of CuTCPP. Figure S8. The standard curve of CuTCPP constructed from UV–vis spectrum at the wavelength of 412 nm. Figure S9. The standard curve of PTX constructed from HPLC measurements at the wavelength of 227 nm. Figure S10. Intracellular drug retention of MCF-7/Taxol cells treated with DiI-labeled PP@PTX NPs, P@PTX NPs, or free FITC-PTX after replacement with fresh culture medium for another 6 h. The scale bar is 50 μm. Figure S11. Bio-TEM images of MCF-7/Taxol cells before (a) and after (b) coincubation with PP@PTX NPs for 3 h. Figure S12. Three-dimensional viewer based on three-dimensional reconstruction of the MCF-7/Taxol spheroid models incubated with DiI-labeled TPP@PTX-CuTCPP for 6 h. Figure S13. Three-dimensional viewer based on three-dimensional reconstruction of the MCF-7/Taxol spheroid models incubated with DiI-labeled PP@PTX-CuTCPP for 6 h. Figure S14. Quantitative fluorescence intensity of NPs with and without tLyP-1 in tumor tissue and the major organs. Data are presented as mean ± SD. **p

In this paper the oxidative degradation process of methyl vanillin wastewater was studied by the subcritical water oxidation (HCWO) technology. A subcritical Fenton oxidation (HCFO) system formed while Fe2+ was added as a catalyst. The oxidation degradation kinetics of methyl vanillin wastewater was also studied. The results showed that the suitable process conditions for degradation of methyl vanillin wastewater by HCWO were as follows: temperature of 340 ​°C, pressure of 24 ​MPa, oxidant multiple of 1.5, residence time of 217.3 ​s (flow rate of 2.0 ​mL ​min-1). For methyl vanillin wastewater, the HCFO system has no obvious advantages compared to the HCWO system. The activation energy (Ea) of HCWO oxidized methyl vanillin wastewater reaction was 32.6 ​kJ ​mol-1, and the pre-exponential factor A was 5.64 s-1.

The wide applications of pure titanium (Ti) are greatly limited by its low strength and hardness. In this paper, we employed an industrial method of rotary swaging (RS) to improve the strength of commercial pure (CP) Ti and uncovered the elementary mechanisms governing microstructural changes under RS. Specifically, the {10-12} extension and {11-22} contraction twins take place in the coarse grains at the early stage of RS deformation, which contributes to the increase of yield strength and moderate ductility. As for the late stage, the twins disappear and are replaced by textured nanostructured grains; meanwhile, there exists a hardness gradient along the radial sample direction. High strain rate RS brings about profuse twins and rapid grain refinement at room temperature in contrast to conventional severe plastic deformation. We rationalize that the high yield strength of CP Ti (up to 955 MPa) is attributed to dislocation, grain boundary and texture strengthening. This result may provide some insights in microstructure-based design of metals with superior mechanical properties subjected to this scalable RS technique.

A series of ten 7-quinolinediamines were prepared and evaluated for potential antiparasitic activity against P. berghei, P. cynomolgi, L. donovani and T. rhodesiense. Compounds 1d and 8 showed activity being slightly effective against L. donovani in hamsters.