Real-Time Detection of Cook Assistant Overalls Based on Embedded Reasoning.

Currently, the target detection based on convolutional neural network plays an important role in image recognition, speech recognition and other fields. However, the current network model features a complex structure, a huge number of parameters and resources. These conditions make it difficult to apply in embedded devices with limited computational capabilities and extreme sensitivity to power consumption. In this regard, the application scenarios of deep learning are limited. This paper proposes a real-time detection scheme for cook assistant overalls based on the Hi3559A embedded processor. With YOLOv3 as the benchmark network, this scheme fully mobilizes the hardware acceleration resources through the network model optimization and the parallel processing technology of the processor, and improves the network reasoning speed, so that the embedded device can complete the task of real-time detection on the local device. The experimental results show that through the purposeful cropping, segmentation and in-depth optimization of the neural network according to the specific processor, the neural network can recognize the image accurately. In an application environment where the power consumption is only 5.5 W, the recognition speed of the neural network on the embedded end is increased to about 28 frames (the design requirement was to achieve a recognition speed of 25 frames or more), so that the optimized network can be effectively applied in the back kitchen overalls identification scene.

Efficacy, Safety, and Tumor Marker Inhibition of Apatinib Combined with Conventional Chemotherapy Regimens for Patients with Advanced Triple-Negative Breast Cancer.

OBJECTIVE: Triple-negative breast cancer (TNBC) is an aggressive disease with highly invasive nature and poor outcomes. Due to the absence of specific treatment strategies for this tumor subgroup, patients with TNBC are treated with conventional therapeutics, frequently leading to systemic relapse. In this study, we sought to investigate apatinib combined with conventional chemotherapy regimens in treating patients with advanced TNBC concerning the efficacy, safety, expressions of tumor markers, and patient survival. METHODS: This is a prospective study including 150 cases of advanced TNBC who were randomly arranged into a conventional group and combined group, with 75 cases per group. The patients in the conventional group were treated with conventional chemotherapy, and those in the combined group were treated with apatinib combined with conventional chemotherapy. The peripheral blood was collected from each patient, and carcinoembryonic antigen (CEA), carbohydrate antigen 153 (CA153), and carbohydrate antigen 125 (CA125) were determined. The expressions of nuclear proliferation antigen marker (Ki67), ß-catenin, and E-cadherin were determined in the biopsy collected from each patient. RESULTS: The objective remission rate (ORR) and disease control rate (DCR) (41.33% and 81.33%) in the combined group were notably higher than those in the conventional group (29.33% and 68.00%) (P < 0.05). After treatment, the serum levels of CEA, CA153, and CA125 and the expressions of Ki67 and ß-catenin were declined, but the expression of E-cadherin was increased in both groups; the combined group exhibited lower serum levels of CEA, CA153, and CA125, and the expressions of Ki67 and ß-catenin were concurrent with a higher expression of E-cadherin than the conventional group (P < 0.05). No significant difference was noted between the two groups regarding the occurrence of adverse reactions (P > 0.05). Improved progression-free survival (PFS) was observed in the combined group compared to the conventional group (P < 0.05. CONCLUSION: These findings suggest that apatinib combined with conventional chemotherapy regimens confers a prolonged PFS for treating patients with advanced TNBC.

Functional implications of PABPC1 in the development of ovarian cancer.

This research aimed to probe the expression characteristics of poly(A)-binding protein cytoplasmic 1 (PABPC1) and its role on the phenotype of ovarian cancer (OC) cells and to further investigate the possible underlying mechanism. The expression of PABPC1 was analyzed according to the data from gene expression omnibus, The Cancer Genome Atlas (TCGA) and Oncomine databases and the RNA sequencing data set from TCGA were downloaded for evaluating the prognostic values. We revealed that compared with the healthy samples, PABPC1 was upregulated in OC samples. High expression of PABPC1 had a connection with a shorter survival for patients with OC. Loss and gain of function assays revealed that silencing PABPC1 significantly suppressed the viability, invasion and migration of SK-OV-3 cells, while PABPC1 overexpression in A2780 cells showed the reverse outcomes. Moreover, Western blot demonstrated that silencing PABPC1 notably inactivated the epithelial-mesenchymal transition (EMT) process, while upregulation of PABPC1 promoted the mitigation of epithelial phenotype and the acquisition of mesenchymal phenotype. Taken together, PABPC1 was upregulated in OC cells and served as a carcinogene to promote the OC cell growth and invasion partly by modulating the EMT process, which implied that PABPC1 might be considered as a useful biomarker for OC therapeutics.

A High-Robust Automatic Reading Algorithm of Pointer Meters Based on Text Detection.

Automatic reading of pointer meters is of great significance for efficient measurement of industrial meters. However, existing algorithms are defective in the accuracy and robustness to illumination shooting angle when detecting various pointer meters. Hence, a novel algorithm for adaptive detection of different pointer meters was presented. Above all, deep learning was introduced to detect and recognize scale value text in the meter dial. Then, the image was rectified and meter center was determined based on text coordinate. Next, the circular arc scale region was transformed into a linear scale region by polar transform, and the horizontal positions of pointer and scale line were obtained based on secondary search in the expanded graph. Finally, the distance method was used to read the scale region where the pointer is located. Test results showed that the algorithm proposed in this paper has higher accuracy and robustness in detecting different types of meters.