摘要 :
Among the research methods for HER2 automatic evaluation in recent years, most of the methods using deep learning framework have both segmentation and classification functions. Although these methods provide pathologists with refe...
展开
Among the research methods for HER2 automatic evaluation in recent years, most of the methods using deep learning framework have both segmentation and classification functions. Although these methods provide pathologists with reference lesions, they increase the dependence on dataset and the computational cost. Therefore, we propose a Wide Pyramid Network (WPNet) based on deep learning to solve this problem. Our designed WPNet is different from other neural network models, which is mainly extended in the width of the network, and uses the wide pyramid structure to extract the features of different scales on the image for training. Since HER2 score is determined according to the degree of cell membrane staining and the proportion of cells with different degrees of staining, the WPNet model capable of multi-scale feature extraction can facilitate the determination of HER2 score. Compared with other models, for HER2 score classification based on a small sample set, the proposed model not only accelerates the convergence speed during training, reduces the calculation cost but also improves the classification effect.
收起
摘要 :
Interferometric fiber optic gyroscopes driven by lasers are new hotspots in recent years at home and abroad. Semiconductor lasers are considered to be an alternative to traditional broadband light sources due to their high commerc...
展开
Interferometric fiber optic gyroscopes driven by lasers are new hotspots in recent years at home and abroad. Semiconductor lasers are considered to be an alternative to traditional broadband light sources due to their high commercial maturity, good average wavelength stability, and low intensity noise. However, the semiconductor laser is a highly coherent light source with a narrow linewidth. When it is used in an interferometric fiber optic gyroscope, it will reintroduce non-ideal characteristics such as Rayleigh scattering, Kerr effect, polarization cross-coupling and so on, which will affect the accuracy of the gyroscope. The linewidth of the semiconductor laser is widened before use. Based on the OptiSystem simulation platform, the article builds a semiconductor laser linewidth widening model, and analyzes and evaluates several different phase modulation broadening techniques and their effects. It has certain guiding significance for the experimental design and engineering application of semiconductor laser linewidth broadening.
收起
摘要 :
Interferometric fiber optic gyroscopes driven by lasers are new hotspots in recent years at home and abroad. Semiconductor lasers are considered to be an alternative to traditional broadband light sources due to their high commerc...
展开
Interferometric fiber optic gyroscopes driven by lasers are new hotspots in recent years at home and abroad. Semiconductor lasers are considered to be an alternative to traditional broadband light sources due to their high commercial maturity, good average wavelength stability, and low intensity noise. However, the semiconductor laser is a highly coherent light source with a narrow linewidth. When it is used in an interferometric fiber optic gyroscope, it will reintroduce non-ideal characteristics such as Rayleigh scattering, Kerr effect, polarization cross-coupling and so on, which will affect the accuracy of the gyroscope. The linewidth of the semiconductor laser is widened before use. Based on the OptiSystem simulation platform, the article builds a semiconductor laser linewidth widening model, and analyzes and evaluates several different phase modulation broadening techniques and their effects. It has certain guiding significance for the experimental design and engineering application of semiconductor laser linewidth broadening.
收起
摘要 :
With the rapid development of FOG inertial navigation technology in China, it is possible for FOG inertial navigation system to achieve " one nautical mile in a month" navigation accuracy under temperature control environment. As ...
展开
With the rapid development of FOG inertial navigation technology in China, it is possible for FOG inertial navigation system to achieve " one nautical mile in a month" navigation accuracy under temperature control environment. As the core component of FOG inertial navigation system, the performance of high precision FOG directly affects the accuracy of navigation system. Even in a good temperature control environment, the current performance index of high precision FOG is not enough to support the navigation accuracy of "one mile in January". Broadband ASE light source is widely used in high precision fiber optic gyroscopes. The low temporal coherence of the light source is conducive to improving the noise level and bias stability of the gyroscope. With further research, If the output power of ASE light source exceeds a certain level (The power detected by photoelectric detector greater than lOuw), it is found that the relative intensity noise(RIN) of the light source will be the main noise of the FOG. On the basis of studying the sources of fundamental noises (especially intensity noise) in high precision FOG, this paper puts forward the technology of suppressing the noise of high precision FOG, and further designs (large ring size and fiber length) and develops a prototype of high precision FOG with noise suppression technology. The test results of the prototype demonstrate the effectiveness of the suppression technique (for example, ALLAN variance comparison results before and after using suppression technique). The prototype of the accuracy is expected to approach the navigation accuracy of" one nautical mile in a month " through further testing in the FOG inertial navigation system.
收起
摘要 :
In recent years, a single medical image is prone to lose hidden features with low resolution and salient features with high noise but rich information, ignoring the connection of multiple images. Therefore, to remedy for the short...
展开
In recent years, a single medical image is prone to lose hidden features with low resolution and salient features with high noise but rich information, ignoring the connection of multiple images. Therefore, to remedy for the shortcomings, this paper proposes a multi-modal medical image classification method combined with graph convolutional neural networks(MB-pGCN). First, for the first modality image, we use the ResNet-152 model to extract features, and obtain local disease-related region features with the inter-group comparison method. It utilizes weak attention learning to extract local salient features. For the second modality, we use the patch extraction method to embed. Then it combines the acquired local image features and uses the complementary information carried by the modalities to construct a graph convolutional neural network, designing the convergence layer to achieve graph pooling, which takes advantage of the node features and the local structural relationships between nodes. Ultimately, it splices global features with local features to achieve classification. To validate the proposed classification model framework, we choose ADNI, COVID-19 datasets that are in line with the research, showing that MB-pGCN outperforms other models.
收起
摘要 :
As a mature product with high commercialization, the fiber optic gyroscope is susceptible to the influence of environmental factors in actual use, which affects the measurement accuracy. In order to improve the temperature adaptab...
展开
As a mature product with high commercialization, the fiber optic gyroscope is susceptible to the influence of environmental factors in actual use, which affects the measurement accuracy. In order to improve the temperature adaptability of the fiber optic gyroscope and improve the efficiency of temperature compensation in the engineering process of the gyroscope, a temperature modeling and compensation method based on a multilayer perceptron is proposed. First, based on the working principle of the fiber optic gyroscope, the mechanism that causes the temperature error of the fiber optic gyroscope is analyzed. Then, based on the neural network model of the multilayer perceptron, the structure design of the temperature compensation model of the fiber optic gyroscope is carried out, and the existing data is used to train the model. Finally, the compensation model was verified by experiments. The results show that the bias stability of the gyro can be improved by 80% after compensation using this model. Although this method requires a lot of calculations in the early stage, after the model parameters are solidified, it has strong adaptability, is easy to implement in engineering, and can effectively improve engineering efficiency.
收起
摘要 :
As a mature product with high commercialization, the fiber optic gyroscope is susceptible to the influence of environmental factors in actual use, which affects the measurement accuracy. In order to improve the temperature adaptab...
展开
As a mature product with high commercialization, the fiber optic gyroscope is susceptible to the influence of environmental factors in actual use, which affects the measurement accuracy. In order to improve the temperature adaptability of the fiber optic gyroscope and improve the efficiency of temperature compensation in the engineering process of the gyroscope, a temperature modeling and compensation method based on a multilayer perceptron is proposed. First, based on the working principle of the fiber optic gyroscope, the mechanism that causes the temperature error of the fiber optic gyroscope is analyzed. Then, based on the neural network model of the multilayer perceptron, the structure design of the temperature compensation model of the fiber optic gyroscope is carried out, and the existing data is used to train the model. Finally, the compensation model was verified by experiments. The results show that the bias stability of the gyro can be improved by 80% after compensation using this model. Although this method requires a lot of calculations in the early stage, after the model parameters are solidified, it has strong adaptability, is easy to implement in engineering, and can effectively improve engineering efficiency.
收起
摘要 :
Dongsheng deposit at the northeast Ordos Basin is one of the largest sandstone-type uranium deposits in China. Its characteristics are quite different from that of sandstone-type uranium deposit in Turpan Basin and Yili Basin, Xin...
展开
Dongsheng deposit at the northeast Ordos Basin is one of the largest sandstone-type uranium deposits in China. Its characteristics are quite different from that of sandstone-type uranium deposit in Turpan Basin and Yili Basin, Xinjiang province. One of the important aspects is that Zhiluo group of ore-bearing stratum in Dongsheng deposit was developed with more discontinuous lenticular carbonation and phenomenon of calcified wood rather than the unique non-plant fossils. This phenomenon of calcified-wood alike carbonation is rarely observed in other uranium deposits in Ordos Basin. The identified rock slice is composed of micritic calcite cemented sandstone and crystalline calcite. The former was formed by sedimentary diagenesis. The latter consists of calcite inclusions, which have been observed in water-based solution and CO_2 or CH_4-based gas inclusions. The temperature of the most inclusions were in the range of 140~170℃. It indicated that carbonate played an important role as hydrothermal fludis in the process of the formation of calcified wood. The analytic results of sparry calcite carbon and oxygen isotope showed that the most of the carbon sources were provided by the organic matter rather than from the process of diagenesis. Combined with the formation and characteristics of Dongsheng deposit where the area oil and gas dispersion exists, the formation of calcified-wood alike carbonation was the result of geological dispersion of oil and gas, which came from the middle of the basin area in the Paleozoic atmosphere filled by calcite crystals. Understanding the formation mechanism of Zhiluo group of ore-bearing stratum has great significance in prospecting for Dongsheng deposit.
收起
摘要 :
Dongsheng deposit at the northeast Ordos Basin is one of the largest sandstone-type uranium deposits in China. Its characteristics are quite different from that of sandstone-type uranium deposit in Turpan Basin and Yili Basin, Xin...
展开
Dongsheng deposit at the northeast Ordos Basin is one of the largest sandstone-type uranium deposits in China. Its characteristics are quite different from that of sandstone-type uranium deposit in Turpan Basin and Yili Basin, Xinjiang province. One of the important aspects is that Zhiluo group of ore-bearing stratum in Dongsheng deposit was developed with more discontinuous lenticular carbonation and phenomenon of calcified wood rather than the unique non-plant fossils. This phenomenon of calcified-wood alike carbonation is rarely observed in other uranium deposits in Ordos Basin. The identified rock slice is composed of micritic calcite cemented sandstone and crystalline calcite. The former was formed by sedimentary diagenesis. The latter consists of calcite inclusions, which have been observed in water-based solution and CO_2 or CH_4-based gas inclusions. The temperature of the most inclusions were in the range of 140-170°C.
收起
摘要 :
Dongsheng deposit at the northeast Ordos Basin is one of the largest sandstone-type uranium deposits in China. Its characteristics are quite different from that of sandstone-type uranium deposit in Turpan Basin and Yili Basin, Xin...
展开
Dongsheng deposit at the northeast Ordos Basin is one of the largest sandstone-type uranium deposits in China. Its characteristics are quite different from that of sandstone-type uranium deposit in Turpan Basin and Yili Basin, Xinjiang province. One of the important aspects is that Zhiluo group of ore-bearing stratum in Dongsheng deposit was developed with more discontinuous lenticular carbonation and phenomenon of calcified wood rather than the unique non-plant fossils. This phenomenon of calcified-wood alike carbonation is rarely observed in other uranium deposits in Ordos Basin. The identified rock slice is composed of micritic calcite cemented sandstone and crystalline calcite. The former was formed by sedimentary diagenesis. The latter consists of calcite inclusions, which have been observed in water-based solution and CO_2 or CH_4-based gas inclusions. The temperature of the most inclusions were in the range of 140~170°C. It indicated that carbonate played an important role as hydrothermal fludis in the process of the formation of calcified wood. The analytic results of sparry calcite carbon and oxygen isotope showed that the most of the carbon sources were provided by the organic matter rather than from the process of diagenesis. Combined with the formation and characteristics of Dongsheng deposit where the area oil and gas dispersion exists, the formation of calcified-wood alike carbonation was the result of geological dispersion of oil and gas, which came from the middle of the basin area in the Paleozoic atmosphere filled by calcite crystals. Understanding the formation mechanism of Zhiluo group of ore-bearing stratum has great significance in prospecting for Dongsheng deposit.
收起