Pulse decomposition has been proven to be efficient to analyze complicated signals and it is introduced into the photo-acoustic and thermo-acoustic tomography to eliminate reconstruction distortions caused by negative...Pulse decomposition has been proven to be efficient to analyze complicated signals and it is introduced into the photo-acoustic and thermo-acoustic tomography to eliminate reconstruction distortions caused by negative lobes.During image reconstruction,negative lobes bring errors in the estimation of acoustic pulse amplitude,which is closely related to the distribution of absorption coefficient.The negative lobe error degrades imaging quality seriously in limited-view conditions because it cannot be offset so well as in full-view conditions.Therefore,a pulse decomposition formula is provided with detailed deduction to eliminate the negative lobe error and is incorporated into the popular delay-and-sum method for better reconstructing the image without additional complicated computation.Numerical experiments show that the pulse decomposition improves the image quality obviously in the limited-view conditions,such as separating adjacent absorbers,discovering a small absorber despite disturbance from a big absorber nearby,etc.展开更多
Since the early 20th century,China has gradually established a clinical,educational,and research system centered around modern scientific medicine,which has now become the dominant force in China's medical and hea...Since the early 20th century,China has gradually established a clinical,educational,and research system centered around modern scientific medicine,which has now become the dominant force in China's medical and health system and services,with the construction and development of the Chinese Academy of Medical Sciences and Peking Union Medical College as the most prominent symbol.The scientific medicine in the new era requires close cooperation across multiple disciplines and fields to build a high-quality and efficient medical and health service system.It also involves combining the excellent traditional Chinese culture with Western medicine to explore a unique path of modern scientific medicine with Chinese characteristics.展开更多
In the production of the sucker rod well, the dynamic liquid level is important for the production efficiency and safety in the lifting process. It is influenced by multi-source data which need to be combined for the ...In the production of the sucker rod well, the dynamic liquid level is important for the production efficiency and safety in the lifting process. It is influenced by multi-source data which need to be combined for the dynamic liquid level real-time calculation. In this paper, the multi-source data are regarded as the different views including the load of the sucker rod and liquid in the wellbore, the image of the dynamometer card and production dynamics parameters. These views can be fused by the multi-branch neural network with special fusion layer. With this method, the features of different views can be extracted by considering the difference of the modality and physical meaning between them. Then, the extraction results which are selected by multinomial sampling can be the input of the fusion layer.During the fusion process, the availability under different views determines whether the views are fused in the fusion layer or not. In this way, not only the correlation between the views can be considered, but also the missing data can be processed automatically. The results have shown that the load and production features fusion(the method proposed in this paper) performs best with the lowest mean absolute error(MAE) 39.63 m, followed by the features concatenation with MAE 42.47 m. They both performed better than only a single view and the lower MAE of the features fusion indicates that its generalization ability is stronger. In contrast, the image feature as a single view contributes little to the accuracy improvement after fused with other views with the highest MAE. When there is data missing in some view, compared with the features concatenation, the multi-view features fusion will not result in the unavailability of a large number of samples. When the missing rate is 10%, 30%, 50% and 80%, the method proposed in this paper can reduce MAE by 5.8, 7, 9.3 and 20.3 m respectively. In general, the multi-view features fusion method proposed in this paper can improve the accuracy obviously and process the missing data effectively, which helps provide technical support for real-time monitoring of the dynamic liquid level in oil fields.展开更多
基金supported by the National Basic Research Program of China(Grant No.2012CB921504)the National Natural Science Foundation of China(Grant Nos.11274167,11274171,61201450,61201495,and 61302175)the Chongqing Science and Technology Commission of China(Grant Nos.2012jjA40058 and 2012jjA40006)
文摘Pulse decomposition has been proven to be efficient to analyze complicated signals and it is introduced into the photo-acoustic and thermo-acoustic tomography to eliminate reconstruction distortions caused by negative lobes.During image reconstruction,negative lobes bring errors in the estimation of acoustic pulse amplitude,which is closely related to the distribution of absorption coefficient.The negative lobe error degrades imaging quality seriously in limited-view conditions because it cannot be offset so well as in full-view conditions.Therefore,a pulse decomposition formula is provided with detailed deduction to eliminate the negative lobe error and is incorporated into the popular delay-and-sum method for better reconstructing the image without additional complicated computation.Numerical experiments show that the pulse decomposition improves the image quality obviously in the limited-view conditions,such as separating adjacent absorbers,discovering a small absorber despite disturbance from a big absorber nearby,etc.
基金Supported by the Study on Chen Zhiqian's Public Health Thought Theory and Practice in Urban and Rural Areas(No.:3332022175).
文摘Since the early 20th century,China has gradually established a clinical,educational,and research system centered around modern scientific medicine,which has now become the dominant force in China's medical and health system and services,with the construction and development of the Chinese Academy of Medical Sciences and Peking Union Medical College as the most prominent symbol.The scientific medicine in the new era requires close cooperation across multiple disciplines and fields to build a high-quality and efficient medical and health service system.It also involves combining the excellent traditional Chinese culture with Western medicine to explore a unique path of modern scientific medicine with Chinese characteristics.
基金supported by the National Natural Science Foundation of China under Grant 52325402, 52274057, 52074340 and 51874335the National Key R&D Program of China under Grant 2023YFB4104200+1 种基金the Major Scientific and Technological Projects of CNOOC under Grant CCL2022RCPS0397RSN111 Project under Grant B08028。
文摘In the production of the sucker rod well, the dynamic liquid level is important for the production efficiency and safety in the lifting process. It is influenced by multi-source data which need to be combined for the dynamic liquid level real-time calculation. In this paper, the multi-source data are regarded as the different views including the load of the sucker rod and liquid in the wellbore, the image of the dynamometer card and production dynamics parameters. These views can be fused by the multi-branch neural network with special fusion layer. With this method, the features of different views can be extracted by considering the difference of the modality and physical meaning between them. Then, the extraction results which are selected by multinomial sampling can be the input of the fusion layer.During the fusion process, the availability under different views determines whether the views are fused in the fusion layer or not. In this way, not only the correlation between the views can be considered, but also the missing data can be processed automatically. The results have shown that the load and production features fusion(the method proposed in this paper) performs best with the lowest mean absolute error(MAE) 39.63 m, followed by the features concatenation with MAE 42.47 m. They both performed better than only a single view and the lower MAE of the features fusion indicates that its generalization ability is stronger. In contrast, the image feature as a single view contributes little to the accuracy improvement after fused with other views with the highest MAE. When there is data missing in some view, compared with the features concatenation, the multi-view features fusion will not result in the unavailability of a large number of samples. When the missing rate is 10%, 30%, 50% and 80%, the method proposed in this paper can reduce MAE by 5.8, 7, 9.3 and 20.3 m respectively. In general, the multi-view features fusion method proposed in this paper can improve the accuracy obviously and process the missing data effectively, which helps provide technical support for real-time monitoring of the dynamic liquid level in oil fields.
