Breast cancer is a serious and high morbidity disease in women,and it is the main cause of cancer death in China.However,getting tested and diagnosed early can reduce the risk of cancer.At present,there are clinical e...Breast cancer is a serious and high morbidity disease in women,and it is the main cause of cancer death in China.However,getting tested and diagnosed early can reduce the risk of cancer.At present,there are clinical examinations,imaging screening and biopsies,among which histopathological examination is the gold standard.However,the process is complicated and time-consuming,and misdiagnosis may exist.This paper puts forward a classification framework based on deep learning,introducing multi-attention mechanism,selecting kernel convolution instead of ordinary convolution,and using different weights and combinations to pay attention to the accuracy index and growth rate of the model.In addition,we also compared the learning rate regulators.Error function can fine-tune the learning rate to achieve good performance,using label softening to reduce the loss error caused by model error recognition in the label,and assigning different category weights in the loss function to balance the positive and negative samples.We used the BreakHis data set to automatically classify histological images into benign and malignant,four categories and eight subtypes.Experimental results showed that the accuracy of binary classifications ranged from 98.23%to 98.83%,and that of multiple classifications ranged from 97.89%to 98.11%.展开更多
For safety reasons,in the automated dispensing medicines process,robots and humans cooperate to accomplish the task of drug sorting and distribution.In this dynamic unstructured environment,such as a humanrobot collab...For safety reasons,in the automated dispensing medicines process,robots and humans cooperate to accomplish the task of drug sorting and distribution.In this dynamic unstructured environment,such as a humanrobot collaboration scenario,the safety of human,robot,and equipment in the environment is paramount.In this work,a practical and effective robot motion planning method is proposed for dynamic unstructured environments.To figure out the problems of blind zones of single depth sensor and dynamic obstacle avoidance,we first propose a method for establishing offline mapping and online fusion of multi-sensor depth images and 3D grids of the robot workspace,which is used to determine the occupation states of the 3D grids occluded by robots and obstacles and to conduct real-time estimation of the minimum distance between the robot and obstacles.Then,based on the reactive control method,the attractive and repulsive forces are calculated and transformed into robot joint velocities to avoid obstacles in real time.Finally,the robot’s dynamic obstacle avoidance ability is evaluated on an experimental platform with a UR5 robot and two KinectV2 RGB-D sensors,and the effectiveness of the proposed method is verified.展开更多
The aim of the study was to investigate whether phosphorus(P) transporters, type IIb sodium-dependent phosphate cotransporter(NaP-IIb) and inorganic phosphate transporter 2(PiT2), were directly involved in P absorptio...The aim of the study was to investigate whether phosphorus(P) transporters, type IIb sodium-dependent phosphate cotransporter(NaP-IIb) and inorganic phosphate transporter 2(PiT2), were directly involved in P absorption across primary cultured duodenal epithelial cell monolayers of chick embryos. The siRNAs against NaP-IIb or PiT2 were designed, synthesized and transfected into primary cultured duodenal epithelial cells of chick embryos. Then, the inhibitory efficiency of siRNAs against NaP-IIb or PiT2 was analyzed, and the most efficacious siRNAs were selected to be used for subsequent P absorption experiments. Briefly, primary cultured duodenal epithelial cells of chick embryos were transfected with either NaP-IIb or PiT2 siRNAs and grown in confluent monolayers on transwell plates. The untransfected or transfected cell monolayers were then incubated in an uptake medium containing 0 or 0.25 mmol L^(–1) of P as KH_(2) PO_(4) to measure the P absorption across duodenal epithelial cell monolayers. The results showed that among the siRNAs designed, si-1372 and si-890 were demonstrated to be the most effective in inhibiting the NaPIIb and PiT2 expressions, respectively. Supplemental P increased(P=0.065) the protein abundance of PiT2 and enhanced(P<0.0001) P absorption in primary cultured duodenal epithelial cell of chick embryos. Furthermore, NaPIIb silencing decreased(P=0.07) P absorption across duodenal epithelial cell monolayers, while PiT2 silencing had no effect(P=0.345). It is concluded that the NaP-IIb, but not PiT2, might be directly involved in the P absorption of chick duodenal epithelial cells.展开更多
Undesirable repulsive force between contact members due to both a current path shrink near a real contact area and/or so-called pinch effect is particularly onerous for power switch applications, and results in either...Undesirable repulsive force between contact members due to both a current path shrink near a real contact area and/or so-called pinch effect is particularly onerous for power switch applications, and results in either contact floating or bouncing which are associated with an electric arc following contact welding. This problem is of great importance for any circuit breaker especially for compact low voltage vacuum circuit breakers. To avoid contact floating at closure and during any inrush current under short circuit conditions, the electrodynamic repulsive force can be employed successfully if we use a special compensation system flexibly combined with the contact itself. However to select and design the compensation system properly, its efficiency has to be known. This paper presents an approach to obtain the electrodynamic force value depending on different shaped (rectangular, square, circle and arch) copper plates used in the compensator by using ANSYS for current values 40 kA RMS. Curve-fitting was done according to the calculating results, the optimization designing of compensation unit is based on them.展开更多
基金the University Synergy Innovation Program of Anhui Province(No.GXXT-2022-041)。
文摘Breast cancer is a serious and high morbidity disease in women,and it is the main cause of cancer death in China.However,getting tested and diagnosed early can reduce the risk of cancer.At present,there are clinical examinations,imaging screening and biopsies,among which histopathological examination is the gold standard.However,the process is complicated and time-consuming,and misdiagnosis may exist.This paper puts forward a classification framework based on deep learning,introducing multi-attention mechanism,selecting kernel convolution instead of ordinary convolution,and using different weights and combinations to pay attention to the accuracy index and growth rate of the model.In addition,we also compared the learning rate regulators.Error function can fine-tune the learning rate to achieve good performance,using label softening to reduce the loss error caused by model error recognition in the label,and assigning different category weights in the loss function to balance the positive and negative samples.We used the BreakHis data set to automatically classify histological images into benign and malignant,four categories and eight subtypes.Experimental results showed that the accuracy of binary classifications ranged from 98.23%to 98.83%,and that of multiple classifications ranged from 97.89%to 98.11%.
基金the Interdisciplinary Program of Shanghai Jiao Tong University(No.YG2019QNA25)。
文摘For safety reasons,in the automated dispensing medicines process,robots and humans cooperate to accomplish the task of drug sorting and distribution.In this dynamic unstructured environment,such as a humanrobot collaboration scenario,the safety of human,robot,and equipment in the environment is paramount.In this work,a practical and effective robot motion planning method is proposed for dynamic unstructured environments.To figure out the problems of blind zones of single depth sensor and dynamic obstacle avoidance,we first propose a method for establishing offline mapping and online fusion of multi-sensor depth images and 3D grids of the robot workspace,which is used to determine the occupation states of the 3D grids occluded by robots and obstacles and to conduct real-time estimation of the minimum distance between the robot and obstacles.Then,based on the reactive control method,the attractive and repulsive forces are calculated and transformed into robot joint velocities to avoid obstacles in real time.Finally,the robot’s dynamic obstacle avoidance ability is evaluated on an experimental platform with a UR5 robot and two KinectV2 RGB-D sensors,and the effectiveness of the proposed method is verified.
基金supported by the Key Program of the National Natural Science Foundation of China(31630073)the National Natural Science Foundation of China(31472116)+2 种基金the National Key R&D Program of China(2017YFD0502200)the China Agriculture Research System of MOF and MARA(CARS-41)the Agricultural Science and Technology Innovation Program(ASTIP-IAS09)。
文摘The aim of the study was to investigate whether phosphorus(P) transporters, type IIb sodium-dependent phosphate cotransporter(NaP-IIb) and inorganic phosphate transporter 2(PiT2), were directly involved in P absorption across primary cultured duodenal epithelial cell monolayers of chick embryos. The siRNAs against NaP-IIb or PiT2 were designed, synthesized and transfected into primary cultured duodenal epithelial cells of chick embryos. Then, the inhibitory efficiency of siRNAs against NaP-IIb or PiT2 was analyzed, and the most efficacious siRNAs were selected to be used for subsequent P absorption experiments. Briefly, primary cultured duodenal epithelial cells of chick embryos were transfected with either NaP-IIb or PiT2 siRNAs and grown in confluent monolayers on transwell plates. The untransfected or transfected cell monolayers were then incubated in an uptake medium containing 0 or 0.25 mmol L^(–1) of P as KH_(2) PO_(4) to measure the P absorption across duodenal epithelial cell monolayers. The results showed that among the siRNAs designed, si-1372 and si-890 were demonstrated to be the most effective in inhibiting the NaPIIb and PiT2 expressions, respectively. Supplemental P increased(P=0.065) the protein abundance of PiT2 and enhanced(P<0.0001) P absorption in primary cultured duodenal epithelial cell of chick embryos. Furthermore, NaPIIb silencing decreased(P=0.07) P absorption across duodenal epithelial cell monolayers, while PiT2 silencing had no effect(P=0.345). It is concluded that the NaP-IIb, but not PiT2, might be directly involved in the P absorption of chick duodenal epithelial cells.
文摘Undesirable repulsive force between contact members due to both a current path shrink near a real contact area and/or so-called pinch effect is particularly onerous for power switch applications, and results in either contact floating or bouncing which are associated with an electric arc following contact welding. This problem is of great importance for any circuit breaker especially for compact low voltage vacuum circuit breakers. To avoid contact floating at closure and during any inrush current under short circuit conditions, the electrodynamic repulsive force can be employed successfully if we use a special compensation system flexibly combined with the contact itself. However to select and design the compensation system properly, its efficiency has to be known. This paper presents an approach to obtain the electrodynamic force value depending on different shaped (rectangular, square, circle and arch) copper plates used in the compensator by using ANSYS for current values 40 kA RMS. Curve-fitting was done according to the calculating results, the optimization designing of compensation unit is based on them.
