当前工业指针式仪表读数过程中存在特殊环境下依赖人工和推理精度低等问题,本文提出一种基于改进U2-Net的指针式仪表读数方法。针对目前仪表识别算法推理精度差和模型参数数量过多的问题,将U2-Net编码阶段的RSU4和RSU5的最深层的两个卷...当前工业指针式仪表读数过程中存在特殊环境下依赖人工和推理精度低等问题,本文提出一种基于改进U2-Net的指针式仪表读数方法。针对目前仪表识别算法推理精度差和模型参数数量过多的问题,将U2-Net编码阶段的RSU4和RSU5的最深层的两个卷积更换成深度可分离卷积,并在每个RSU的编码阶段后加入了ECA注意力模块,使模型更好地关注指针和刻度区域,提高指针和刻度的识别精度。本文在收集到的数据集上进行评估,通过对比实验表明,相较于SegNet、Deeplabv3+及U2-Net方法,本文改进的模型查准率达到94.58%,针对两种量程25 MPa和1.6 MPa的压力仪表读数引用误差达到1.012%,具有较好的性能表现。At present, there are some problems in the reading process of industrial pointer instruments, such as relying on manual work and low reasoning accuracy. This paper proposes a reading method for pointer instruments based on improved U2-Net. Aiming at the problems of poor reasoning accuracy and too many model parameters in the current instrument identification algorithm, the deepest two convolutions of RSU4 and RSU5 in the U2-Net coding stage are replaced by deep separable convolutions, and the ECA attention module is added after each RSU coding stage, which made the model pay more attention to the pointer and scale area and improved the recognition accuracy of pointer and scale. In this paper, the collected data sets are evaluated. Compared with SegNet, Deeplabv3+ and U2-Net methods, the accuracy of the improved model in this paper reaches 94.58%, and the reference error of pressure instruments with two measuring ranges of 25 MPa and 1.6 MPa reaches 1.012%, which has good performance.展开更多
Myocardial infarction(MI)is characterized by focal necrosis resulting from prolonged myocardial ischemia due to coronary artery obstruction.Vascular reconstruction following MI is crucial for improving cardiac functio...Myocardial infarction(MI)is characterized by focal necrosis resulting from prolonged myocardial ischemia due to coronary artery obstruction.Vascular reconstruction following MI is crucial for improving cardiac function and preventing recurrent infarction.This study investigates the interaction between macrophages and endothelial cells in angiogenesis mediated by nicotinamide mononucleotide(NMN)-induced secretion of macrophage-derived exosomes.We focus on the role of U2 small nuclear RNA auxiliary factor 1(U2af1)gene,a member of the splicing factor serine and arginine(SR)gene family,in the regulation of angiogenesis.Through cardiac ultrasound,Masson staining,2,3,5-triphenyltetrazolium chloride(TTC)staining,Microfil vascular perfusion,and platelet and endothelial cell adhesion molecule 1(CD31)immunofluorescence staining,extracellular vesicles from NMN-stimulated macrophages were shown to exert a protective effect in MI,with proteomic analysis identifying U2AF1 as a candidate protein involved in MI protection.Plasma U2AF1 levels were measured in 70 MI patients,revealing significantly lower levels in individuals with poor coronary collateral vessel(CCV;Rentrop scores 0–1)than in those with good CCV(Rentrop scores 2–3).In both myocardial and hindlimb ischemia mouse models,overexpression of endothelial cell-specific adenoviral overexpression U2AF1 promoted angiogenesis in the heart and hindlimbs and improved cardiac function after MI.Mechanistic studies demonstrated that U2AF1 regulates the alternative splicing(AS)of Yes1-associated transcriptional regulator(Yap1)gene,influencing post-MI angiogenesis and cardiac function recovery.Collectively,our clinical findings suggest that U2AF1 may serve as a therapeutic target for coronary collateral angiogenesis following MI.Given the low immunogenicity and high biosafety of exosomes,this study provides a foundational basis and translational potential for exosome-based therapies in MI treatment.展开更多
文摘当前工业指针式仪表读数过程中存在特殊环境下依赖人工和推理精度低等问题,本文提出一种基于改进U2-Net的指针式仪表读数方法。针对目前仪表识别算法推理精度差和模型参数数量过多的问题,将U2-Net编码阶段的RSU4和RSU5的最深层的两个卷积更换成深度可分离卷积,并在每个RSU的编码阶段后加入了ECA注意力模块,使模型更好地关注指针和刻度区域,提高指针和刻度的识别精度。本文在收集到的数据集上进行评估,通过对比实验表明,相较于SegNet、Deeplabv3+及U2-Net方法,本文改进的模型查准率达到94.58%,针对两种量程25 MPa和1.6 MPa的压力仪表读数引用误差达到1.012%,具有较好的性能表现。At present, there are some problems in the reading process of industrial pointer instruments, such as relying on manual work and low reasoning accuracy. This paper proposes a reading method for pointer instruments based on improved U2-Net. Aiming at the problems of poor reasoning accuracy and too many model parameters in the current instrument identification algorithm, the deepest two convolutions of RSU4 and RSU5 in the U2-Net coding stage are replaced by deep separable convolutions, and the ECA attention module is added after each RSU coding stage, which made the model pay more attention to the pointer and scale area and improved the recognition accuracy of pointer and scale. In this paper, the collected data sets are evaluated. Compared with SegNet, Deeplabv3+ and U2-Net methods, the accuracy of the improved model in this paper reaches 94.58%, and the reference error of pressure instruments with two measuring ranges of 25 MPa and 1.6 MPa reaches 1.012%, which has good performance.
基金supported by the National Natural Science Founda-tion of China(82370417,82330011,and U21A20339)the Science Fund for Distinguished Young Scholars of Heilongjiang Province(JQ2024H001)the Heilongjiang Provincial Postdoctoral Science Foundation(LBH-Z23212).
文摘Myocardial infarction(MI)is characterized by focal necrosis resulting from prolonged myocardial ischemia due to coronary artery obstruction.Vascular reconstruction following MI is crucial for improving cardiac function and preventing recurrent infarction.This study investigates the interaction between macrophages and endothelial cells in angiogenesis mediated by nicotinamide mononucleotide(NMN)-induced secretion of macrophage-derived exosomes.We focus on the role of U2 small nuclear RNA auxiliary factor 1(U2af1)gene,a member of the splicing factor serine and arginine(SR)gene family,in the regulation of angiogenesis.Through cardiac ultrasound,Masson staining,2,3,5-triphenyltetrazolium chloride(TTC)staining,Microfil vascular perfusion,and platelet and endothelial cell adhesion molecule 1(CD31)immunofluorescence staining,extracellular vesicles from NMN-stimulated macrophages were shown to exert a protective effect in MI,with proteomic analysis identifying U2AF1 as a candidate protein involved in MI protection.Plasma U2AF1 levels were measured in 70 MI patients,revealing significantly lower levels in individuals with poor coronary collateral vessel(CCV;Rentrop scores 0–1)than in those with good CCV(Rentrop scores 2–3).In both myocardial and hindlimb ischemia mouse models,overexpression of endothelial cell-specific adenoviral overexpression U2AF1 promoted angiogenesis in the heart and hindlimbs and improved cardiac function after MI.Mechanistic studies demonstrated that U2AF1 regulates the alternative splicing(AS)of Yes1-associated transcriptional regulator(Yap1)gene,influencing post-MI angiogenesis and cardiac function recovery.Collectively,our clinical findings suggest that U2AF1 may serve as a therapeutic target for coronary collateral angiogenesis following MI.Given the low immunogenicity and high biosafety of exosomes,this study provides a foundational basis and translational potential for exosome-based therapies in MI treatment.
