Search

Deep learning can automatically extract and learn multi-layer feature representations hidden between data, and has been successfully applied in image recognition and segmentation, semantic analysis and other fields. In order to improve restaurant settlement efficiency, save time and cost, this paper proposes a method that uses Convolution Neural Network and Huff transform to joint recognition, conducts preliminary detection of images taken with multiple dishes, uses Huff transform to extract and label individual dishes according to the shape of the plate. Then, the article constructs a convolutional neural network in the classification algorithm. Under different network parameters, this paper experiments on 10 dishes images in the cleaned VireoFood172 dataset. Through continuous optimization of network parameters, the classification accuracy of dishes Top2 has reached 87.2%. Under the fixed environment, the plate can be effectively extracted. It is proved that the method has a certain improvement in performance compared with the traditional dish recognition method, and can provide effective help for dish recognition.

Defect detection is the most important step in the postpartum reprocessing of kiwifruit. However, there are some small defects difficult to detect. The accuracy and speed of existing detection algorithms are difficult to meet the requirements of real-time detection. For solving these problems, we developed a defect detection model based on YOLOv5, which is able to detect defects accurately and at a fast speed. The main contributions of this research are as follows: (1) a small object detection layer is added to improve the model’s ability to detect small defects, (2) we pay attention to the importance of different channels by embedding SELayer, (3) the loss function CIoU is introduced to make the regression more accurate, (4) under the prerequisite of no increase in training cost, we train our model based on transfer learning and use the CosineAnnealing algorithm to improve the effect. The results of the experiment show that the overall performance of the improved network YOLOv5-Ours is better than the original and mainstream detection algorithms. The mAP@0.5 of YOLOv5-Ours has reached 94.7%, which was an improvement of nearly 9%, compared to the original algorithm. Our model only takes 0.1 s to detect a single image, which proves the effectiveness of the model. Therefore, YOLOv5-Ours can well meet the requirements of real-time detection and provides a robust strategy for the kiwi flaw detection system.

Simple Summary This study explored an image-based method for recognizing pigs’ postures during growth and established the world’s first human-annotated pig-posture-recognition dataset, which includes pigs standing, lying, lying on their sides, and exploring (the four common postures). Finally, the pig postures were judged, and good results were obtained in practical applications. Abstract Posture changes in pigs during growth are often precursors of disease. Monitoring pigs’ behavioral activities can allow us to detect pathological changes in pigs earlier and identify the factors threatening the health of pigs in advance. Pigs tend to be farmed on a large scale, and manual observation by keepers is time consuming and laborious. Therefore, the use of computers to monitor the growth processes of pigs in real time, and to recognize the duration and frequency of pigs’ postural changes over time, can prevent outbreaks of porcine diseases. The contributions of this article are as follows: (1) The first human-annotated pig-posture-identification dataset in the world was established, including 800 pictures of each of the four pig postures: standing, lying on the stomach, lying on the side, and exploring. (2) When using a deep separable convolutional network to classify pig postures, the accuracy was 92.45%. The results show that the method proposed in this paper achieves adequate pig-posture recognition in a piggery environment and may be suitable for livestock farm applications.

Background As microRNA-34a (miR-34a) has been suggested to be associated with breast cancer (BC), this study was proposed to explore the underlying mechanism of miR-34a in suppressing BC progression. Methods A total of 123 pairs of tumor tissues and matched nontumor tissues were obtained from patients. Reverse transcription polymerase chain reaction and in situ hybridization were used to detect the differences in miR-34a expression in tissues and cells. Whether Wnt1 is a direct downstream target of miR-34a was confirmed by both bioinformatics target gene prediction and dual-luciferase report assay. Wnt1 and other gene expressions that are related to Wnt/β-catenin signaling pathway were assessed by reverse transcription polymerase chain reaction and western blot when MCF-7A cells were transfected with miR-34a mimic or miR-34a inhibitor. The proliferation, invasion and migration status of MCF-7 cells after transfection were assessed by MTT assay, wound healing assay and transwell assays, respectively. Breast tumor xenograft models on mice were also constructed to determine the effect of miR-34a on breast tumor growth in vivo . Results MiR-34a expression was remarkably down-regulated in BC tissues and cell lines compared with normal tissues and cell lines. Wnt1 was a direct downstream target of miR-34a and low expression of miR-34a contributed to the Wnt/β-catenin signaling pathway activation in MCF-7A cells. MiR-34a inhibited the proliferation, invasion and migration of BC in vitro and breast tumor growth in vivo through deactivating the Wnt/β-catenin signaling pathway. Conclusion MiR-34a may suppress the proliferation and progression of BC via mediating the Wnt/β-catenin signaling pathway.

Triptolide is a diterpene triepoxide compound extracted from the medicinal plant, Tripterygium wilfordii Hook F. The aim of the present study was to determine whether triptolide inhibits the proliferation of breast cancer cells and to further investigate the associated molecular mechanisms. The effects of triptolide on the cell viability of three breast cancer cell lines, specifically, highly metastatic MDA-MB-231, human epidermal growth factor receptor 2-positive BT-474 and estrogen receptor-positive MCF7 cells, were measured using 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide and apoptosis assays. Western blot analysis was performed to investigate the expression levels of β-catenin in the control and triptolide-treated cells. The results demonstrated that triptolide treatment caused cell death in the three types of malignant cell lines. Treatment with 25 nM triptolide for 48 h exhibited marked inhibitory effects on the cell viability of the three types of cells, with greater effects observed in BT-474 cells compared with the other two cell types. When compared with the cells not treated with triptolide, 50 nM triptolide treatment resulted in apoptosis of MDA-MB-231, BT-474 and MCF7 cells with apoptotic rates of ~80%. Western blot analysis indicated that triptolide treatment of MDA-MB-231, BT-474 and MCF7 cells decreased the expression levels of β-catenin to 5–10% of the levels observed in the cells treated with dimethyl sulfoxide only. Therefore, the results of the present study indicate that triptolide induces the apoptosis of breast cancer cells via a mechanism associated with the Wnt/β-catenin signaling pathway.

The effects of temperature on the output power and optimal conditions of Ytterbium-doped double-cladding fiber lasers (YDDFLs) are discussed. Temperature-dependent rate equations for YDDFLs based on Boltzmann distribution are built in two-end pump model. The results show that the output power and the slope efficiency decrease with the increase of temperature. The increase of pump power results in that the effect of the temperature on the output performance increases, and the fiber length is a factor that the effect of the temperature depends on really. Moreover we combine the heat distribution formula with the rate equations and compare the numerical results considering with that not considering the temperature-dependence inside laser cavity, the effect of temperature can be ignored only when the pump power is lower, and the optimal fiber length becomes longer when considering the temperature-dependence.

Matrine is an alkaloid isolated from Sophora flavescens. The present study aimed to determine whether matrine effectively inhibits the proliferation of breast cancer cells, and the underlying mechanism(s) of its antitumor function. The effects of matrine on the cell viability of ER-positive MCF7 cells, HER2-positive BT-474 cells and highly metastatic MDA-MB-231 cells were measured using MTT and apoptosis assays. Western blot analysis was performed to investigate the expression levels of the inhibitor of κB (IκB) kinase β (IKKβ) in cells treated with or without matrine. It was observed that the matrine treatment resulted in the death of the three types of cancer cells, but significantly less toxicity was observed in the control cancer cells. The experimental results also suggested that the antitumor effects of matrine on breast cancer cells may be associated with the downregulation of IKKβ expression by matrine, as indicated by the western blot analysis results. The present results suggested that matrine may be used as an effective drug candidate for treating breast cancers in the future, following further research.

Based on a steady-state rate equations (REs) and heat dissipation model considering both convective and radiative heat transfer, the output performance and temperature distribution of Yb 3+ doped gain guided and index antiguided (GG–IAG) fiber lasers by multipoint distributed pumping are analyzed by numerically solving REs. The results show that high output power and even temperature distribution can be obtained by increasing pump points and lowering the losses at the points; multipoint side pumping is an optimal method to obtain compact high power GG–IAG fiber lasers. The numerical analysis provides some insights for the construction of high power GG–IAG fiber lasers.

The fluorescence emission of Rhodamine 6G molecules at the physically polished nanostructured copper surface with varying thickness of the native oxide layer was investigated. The quenching effect was observed when the dye molecule was directly adsorbed onto the substrate surface without the formative oxide layer. However, the fluorescence was enhanced obviously when the native oxide layer was formed at the substrate surface. The experimental observations were discussed by taking into account the formation of the native oxide layer, the non-radiative energy transfer process and the local surface plasmon resonance at rough copper surface. The study highlights the importance of the native oxide layer formed on the metal substrate in surface enhanced fluorescence.