Pig weight and body size are important indicators for producers. Due to the increasing scale of pig farms, it is increasingly difficult for farmers to quickly and automatically obtain pig weight and ...body size. Due to this problem, we focused on a multiple output regression convolutional neural network (CNN) to estimate pig weight and body size. DenseNet201, ResNet152 V2, Xception and MobileNet V2 were modified into multiple output regression CNNs and trained on modeling data. By comparing the estimated performance of each model on test data, modified Xception was selected as the optimal estimation model. Based on pig height, body shape, and contour, the mean absolute error (MAE) of the model to estimate body weight (BW), shoulder width (SW), shoulder height (SH), hip width (HW), hip width (HH), and body length (BL) were 1.16 kg, 0.33 cm, 1.23 cm, 0.38 cm, 0.66 cm, and 0.75 cm, respectively. The coefficient of determination (R2) value between the estimated and measured results was in the range of 0.9879–0.9973. Combined with the LabVIEW software development platform, this method can estimate pig weight and body size accurately, quickly, and automatically. This work contributes to the automatic management of pig farms.
There exists the contradiction between imaging efficiency and imaging quality for Fourier single-pixel imaging (FSI). Although the deep learning approaches have solved this problem to some extent, ...the reconstruction quality at low sampling rate is still not enough to meet the practical requirements. To solve this problem, inspired by the idea of super-resolution, this paper proposes the paralleled fusing of the U-net and attention mechanism to improve the quality of FSI reconstruction at a low sampling rate. This paper builds a generative adversarial network structure to achieve recovery of high-resolution target images from low-resolution FSI reconstruction results under low sampling rate conditions. Compared with conventional FSI and other deep learning methods based on FSI, the proposed method can get better quality and higher resolution results at low sampling rates in simulation and experiments. This approach is particularly important to high-speed Fourier single pixel imaging applications.
The fluorescence lifetime (τ
f
), emission quantum yield (Φ
f
), absorption and emission spectral data of 20 fluorescein derivatives were measured under the same conditions by using time-correlated ...single photon counting, steady state fluorescence and absorption methods to get comparable data. Based on the results, the factors and mechanism that control the fluorescence properties of the fluorescein dyes are discussed. Both Φ
f
and τ
f
are remarkably dependent on the substitution on either xanthene or phenyl rings, but their ratio (Φ
f
/τ
f
), i.e. rate constant of radiation process, is a constant value (0.20 × 10
9
s
−1
). The rate constant of nonradiation process, on the other hand, is varied with both the structure and the solvent used.
This study aims to verify the time-variant feature of American ginseng (AG) continuous cropping obstacles and to explore the factors impeding continuous cropping. We verified the feature with a ...plant-soil feedback pot experiment and then investigated the factors by comparing the properties of control soils that had not been previously used for growing ginseng (CS) with those of soils with a 10-year-crop-rotation cycle following the growth of AG (RS). It's found that the survival rate of AG in RS was lower than that in CS. The RS had lower pH, available potassium content, and urease activity. Additionally, p-coumaric, p-hydroxybenzoic, vanillic, caffeic, and cinnamic acid levels were lower in RS than in CS, but salicylic acid levels showed the opposite pattern. RS had higher Rhodanobacter and lower Acidothermus, Sphingomonas relative abundances in bacterial community. It's also found that many bacteria were substantially correlated with phenolic acids and soil physiochemical properties. Results indicate that even after 10-year crop rotation, the negative effects of prior continuous cropping of AG has not been eliminated. The growth of AG can be affected negatively with deterioration of soil physicochemical properties and with lower levels of phenolic acids which promote pathogen reproduction. Probiotics reduction also weighs. Moreover, biotic factors are interrelated with abiotic ones. Therefore, it can be inferred that the comprehensive change of soil properties is the main obstacle for continuous cropping.
•Based on the principles of SPEI, we develop a GDAI.•The relationship between GDAI and AI is closer.•The correlation between GDAI and SPEI is also better.
Climate change has increased the risk of ...drought in both arid and non-arid regions of the globe. Therefore, in order to monitor and evaluate global drought and aridity,based on the principle of standardized precipitation evapotranspiration index (SPEI), this paper selected precipitation and potential evapotranspiration data and used a frequency calculation method to develop a multi-scale global drought aridity index (GDAI) that concurrently considers spatial and temporal variation characteristics: the spatiotemporal standardized precipitation evapotranspiration index. The index was compared with the aridity index (AI) and SPEI. The results showed that the correlation coefficients between GDAI and AI were greater than 0.8 in most areas, and the relationship was closer and could reveal the global aridity and wetness zoning. In addition, the correlation between GDAI and SPEI was also better, which could capture the temporal change characteristics of drought. Moreover, this study also compared the grades of GDAI and SPEI with the actual drought grades in Yunnan from September 2009 to August 2010, and found that GDAI was better than SPEI, and GDAI was the most accurately evaluated at the 3 month time scale, with an accuracy rate of 86.11%. Therefore, this index is more helpful for the assessment and monitoring of global drought and aridity.
Accurate semantic editing of the generated images is extremely important for machine learning and sample enhancement of big data. Aiming at the problem of semantic entanglement in generated image ...latent space of the StyleGAN2 network, we proposed a generated image editing method based on global-local Jacobi disentanglement. In terms of global disentanglement, we extract the weight matrix of the style layer in the pre-trained StyleGAN2 network; obtain the semantic attribute direction vector by using the weight matrix eigen decomposition method; finally, utilize this direction vector as the initialization vector for the Jacobi orthogonal regularization search algorithm. Our method improves the speed of the Jacobi orthogonal regularization search algorithm with the proportion of effective semantic attribute editing directions. In terms of local disentanglement, we design a local contrast regularized loss function to relax the semantic association local area and non-local area and utilize the Jacobi orthogonal regularization search algorithm to obtain a more accurate semantic attribute editing direction based on the local area prior MASK. The experimental results show that the proposed method achieves SOTA in semantic attribute disentangled metrics and can discover more accurate editing directions compared with the mainstream unsupervised generated image editing methods.
MicroRNAs (miRNAs) are involved in the maintenance of the cancer stem cell (CSC) phenotype by binding to genes and proteins that modulate cell proliferation and/or cell apoptosis. In our study, we ...aimed to investigate the role of miR-1305 in the proliferation and self-renewal of liver CSCs (LCSCs) via the ubiquitin-conjugating enzyme E2T (UBE2T)-mediated Akt-signaling pathway. Differentially expressed genes in human hepatocellular carcinoma (HCC) were obtained by in silico analysis. The relationship between miR-1305 and UBE2T was verified by dual luciferase reporter gene assay. qRT-PCR and western blot analysis were performed to determine the expression of UBE2T, the Akt-signaling pathway, and stemness-related factors in LCSCs. In addition, miR-1305 disrupted the activation of the Akt-signaling pathway by targeting UBE2T, and, ultimately, it repressed the sphere formation, colony formation, and proliferation, as well as tumorigenicity of LCSCs. In summary, miR-1305 targeted UBE2T to inhibit the Akt-signaling pathway, thereby suppressing the self-renewal and tumorigenicity of LCSCs. Those findings may provide an enhanced understanding of miR-1305 as a therapeutic target to limit the progression of LCSCs.
The mainstream methods for change detection in synthetic-aperture radar (SAR) images use difference images to define the initial change regions. However, methods can suffer from semantic collapse, ...which makes it difficult to determine semantic information about the changes. In this paper, we proposed a hierarchical fusion SAR image change-detection model based on hierarchical fusion conditional random field (HF-CRF). This model introduces multimodal difference images and constructs the fusion energy potential function using dynamic convolutional neural networks and sliding window entropy information. By using an iterative convergence process, the proposed method was able to accurately detect the change-detection regions. We designed a dynamic region convolutional semantic segmentation network with a two-branch structure (D-DRUNet) to accomplish feature fusion and the segmentation of multimodal difference images. The proposed network adopts a dual encoder–single decoder structure where the baseline is the UNet network that utilizes dynamic convolution kernels. D-DRUNet extracts multimodal difference features and completes semantic-level fusion. The Sobel operator is introduced to strengthen the multimodal difference-image boundary information and construct the dynamic fusion pairwise potential function, based on local boundary entropy. Finally, the final change result is stabilized by iterative convergence of the CRF energy potential function. Experimental results demonstrate that the proposed method outperforms existing methods in terms of the overall number of detection errors, and reduces the occurrence of false positives.
•A Fourier single pixel imaging based on a generative adversarial network with high quality is proposed.•The proposed method has the relatively strong reconstruction and generalization ability under ...low sampling rates.•The reconstruction time of the proposed method meets the requirement of real-time imaging.
Single pixel imaging is an innovative imaging scheme using active light to obtain spatial information, which has attracted much attention in the computational imaging field. However, for single pixel imaging, it is a great challenge to find an efficient technique to obtain imaging results with high quality under low sampling conditions. In order to solve this problem, a Fourier single pixel imaging (FSPI) based on a generative adversarial network (GAN) is proposed in this paper. In the proposed GAN model, perceptual loss, pixel and frequency loss are incorporated into the total loss function to better preserve the details of the target. With the help of the GAN model, the FSPI can reconstruct results with high quality at low sampling rate conditions. The numerical simulation and experiment are implemented. Compared with conventional FSPI and FSPI based on a deep convolutional auto-encoder network, the proposed method has a better visual effect and image quality evaluation index. This approach is particularly important to high speed single pixel imaging applications due to its potential for reconstructing the high-quality target image with a low sampling rate.
Salmonella is a major zoonotic foodborne pathogen that persists on poultry farms worldwide. The present study aimed to survey the prevalence of Salmonella and antimicrobial resistance of Salmonella ...enterica serovar Enteritidis (S. Enteritidis) recovered from broiler chickens in Shandong Province, China. A total of 280 Salmonella isolates were identified from 923 broiler chicken samples between 2013 and 2018. Among the isolates, S. Enteritidis (n = 128, 45.7%) was the predominant serovar, and high antimicrobial resistance rates to piperacillin (PIP) (n = 123, 96.1%), ampicillin (AM) (n = 122, 95.3%), nitrofurantoin (FT) (n = 106, 96.1%), and tetracycline (TE) (n = 93, 72.7%) were observed in S. Enteritidis. A total of 96 (75.0%) S. Enteritidis isolates presented with multidrug resistance, the most frequent of which were the combination of AM, PIP, TE, and FT. Resistance to fluoroquinolone tended to increase during 2013 to 2018. Our findings provide important and updated information about the baseline antimicrobial-resistant data for food safety and a risk assessment of S. Enteritidis from broiler chickens in Shandong Province and will be helpful for future surveillance activities to ensure the safety of the chicken supply.