In breast cancer grading,the subtle differences between HE-stained pathological images and the insufficient number of data samples lead to grading inefficiency.With its rapid development,deep learning technology has b...In breast cancer grading,the subtle differences between HE-stained pathological images and the insufficient number of data samples lead to grading inefficiency.With its rapid development,deep learning technology has been widely used for automatic breast cancer grading based on pathological images.In this paper,we propose an integrated breast cancer grading framework based on a fusion deep learning model,which uses three different convolutional neural networks as submodels to extract feature information at different levels from pathological images.Then,the output features of each submodel are learned by the fusion network based on stacking to generate the final decision results.To validate the effectiveness and reliability of our proposed model,we perform dichotomous and multiclassification experiments on the Invasive Ductal Carcinoma(IDC)pathological image dataset and a generated dataset and compare its performance with those of the state-of-the-art models.The classification accuracy of the proposed fusion network is 93.8%,the recall is 93.5%,and the F1 score is 93.8%,which outperforms the state-of-the-art methods.展开更多
An idea is presented about the development of a data processing and analysis system for ICF experiments, which is based on an object oriented framework. The design and preliminary implementation of the data processing...An idea is presented about the development of a data processing and analysis system for ICF experiments, which is based on an object oriented framework. The design and preliminary implementation of the data processing and analysis framework based on the ROOT system have been completed. Software for unfolding soft X-ray spectra has been developed to test the functions of this framework.展开更多
变电站室内无人机巡检可有效降低人工巡检作业强度。由于飞行精度要求高,搭载能力有限,仅依靠无人机搭载摄像头与惯性测量单元(inertial measurement unit, IMU)数据融合确定位姿无法满足精度要求,为此,提出基于变电站室内已有固定摄像...变电站室内无人机巡检可有效降低人工巡检作业强度。由于飞行精度要求高,搭载能力有限,仅依靠无人机搭载摄像头与惯性测量单元(inertial measurement unit, IMU)数据融合确定位姿无法满足精度要求,为此,提出基于变电站室内已有固定摄像头的泛在物联的多视觉-惯导融合框架,针对室内光线情况对无人机摄像头图像进行强化,并与IMU数据结合得到初步的无人机位置数据。进一步通过在无人机上布设二维码(quick response code,QR码),应用改进后的PnP(perspective-n-point)算法优化无人机位姿数据。飞行结束后在无人机机巢对IMU的累计误差进行校验。实验证明:该方法布设与维护的工作量小,相较仅依靠搭载摄像头与IMU数据融合算法,飞行精度有较大提高,可满足变电站内无人机巡检作业的需要。展开更多
文摘In breast cancer grading,the subtle differences between HE-stained pathological images and the insufficient number of data samples lead to grading inefficiency.With its rapid development,deep learning technology has been widely used for automatic breast cancer grading based on pathological images.In this paper,we propose an integrated breast cancer grading framework based on a fusion deep learning model,which uses three different convolutional neural networks as submodels to extract feature information at different levels from pathological images.Then,the output features of each submodel are learned by the fusion network based on stacking to generate the final decision results.To validate the effectiveness and reliability of our proposed model,we perform dichotomous and multiclassification experiments on the Invasive Ductal Carcinoma(IDC)pathological image dataset and a generated dataset and compare its performance with those of the state-of-the-art models.The classification accuracy of the proposed fusion network is 93.8%,the recall is 93.5%,and the F1 score is 93.8%,which outperforms the state-of-the-art methods.
基金This project supported by the National High-Tech Research and Development Plan (863-804-3)
文摘An idea is presented about the development of a data processing and analysis system for ICF experiments, which is based on an object oriented framework. The design and preliminary implementation of the data processing and analysis framework based on the ROOT system have been completed. Software for unfolding soft X-ray spectra has been developed to test the functions of this framework.
