This study proposes a novel general image fusion framework based on cross-domain long-range learning and Swin Transformer,termed as SwinFusion.On the one hand,an attention-guided cross-domain module is devised to achi...This study proposes a novel general image fusion framework based on cross-domain long-range learning and Swin Transformer,termed as SwinFusion.On the one hand,an attention-guided cross-domain module is devised to achieve sufficient integration of complementary information and global interaction.More specifically,the proposed method involves an intra-domain fusion unit based on self-attention and an interdomain fusion unit based on cross-attention,which mine and integrate long dependencies within the same domain and across domains.Through long-range dependency modeling,the network is able to fully implement domain-specific information extraction and cross-domain complementary information integration as well as maintaining the appropriate apparent intensity from a global perspective.In particular,we introduce the shifted windows mechanism into the self-attention and cross-attention,which allows our model to receive images with arbitrary sizes.On the other hand,the multi-scene image fusion problems are generalized to a unified framework with structure maintenance,detail preservation,and proper intensity control.Moreover,an elaborate loss function,consisting of SSIM loss,texture loss,and intensity loss,drives the network to preserve abundant texture details and structural information,as well as presenting optimal apparent intensity.Extensive experiments on both multi-modal image fusion and digital photography image fusion demonstrate the superiority of our SwinFusion compared to the state-of-theart unified image fusion algorithms and task-specific alternatives.Implementation code and pre-trained weights can be accessed at https://github.com/Linfeng-Tang/SwinFusion.展开更多
The human hepatitis B virus （HBV） and the duck hepatitis B virus （DHBV） share several fundamental features. Both viruses have a partially double-stranded DNA genome that is replicated via a RNA intermediate and th...The human hepatitis B virus （HBV） and the duck hepatitis B virus （DHBV） share several fundamental features. Both viruses have a partially double-stranded DNA genome that is replicated via a RNA intermediate and the coding open reading frames （ORFs） overlap extensively. In addition, the genomic and structural organization, as well as replication and biological characteristics, are very similar in both viruses. Host of the key features of hepadnaviral infection were first discovered in the DHBV model system and subsequently confirmed for HBV. There are, however, several differences between human HBV and DHBV. This review will focus on the molecular and cellular biology, evolution, and host adaptation of the avian hepatitis B viruses with particular emphasis on DHBV as a model system.展开更多
A new distributed fusion method of radar/infrared （IR） tracking system based on separation and combination of the measurements is proposed by analyzing the influence of rate measurement. The rate information separat...A new distributed fusion method of radar/infrared （IR） tracking system based on separation and combination of the measurements is proposed by analyzing the influence of rate measurement. The rate information separated from the radar measurements together with measurements of IR form a pseudo vector of IR, and the corresponding filter is designed. The results indicate that the method not only makes a great improvement to the local tracker＇s performance, but also improves the global tracking precision efficiently.展开更多
Background Lumbar pedicle screw fixation and fusion are major procedures for treating discogenic low back pain （DLBP）. However, due to its advantages of preserving the segmental motion and biomechanical simulation, ...Background Lumbar pedicle screw fixation and fusion are major procedures for treating discogenic low back pain （DLBP）. However, due to its advantages of preserving the segmental motion and biomechanical simulation, artificial total lumbar disc replacement （TDR） is increasingly popular. Methods From 2007 to 2010, 68 DLBP patients were enrolled. TDR were performed on 34 patients and the other 34 controls underwent the traditional fixation procedure. Qualitative and quantitative evaluations were followed including the changes in range of motion （ROM） and interpedicle height （IPH） at the posterior intervertebral body of operated level, in 6 and 12 months, and 3 years, postoperatively. Results Qualitative results showed satisfying improvement in the two groups after 6 and 12 months, respectively, and the inter-group differences were significant （P 〉0.05）. The results of ROM and IPH have shown significant differences between the TDR and spinal fusion groups （P 〈0.05）. Conclusion With similar clinical improvements as the traditional spinal fusion method, TDR offered significantly better ROM and intervertebral foramen hei.qht.展开更多
In order to extract the richer feature information of ship targets from sea clutter, and address the high dimensional data problem, a method termed as multi-scale fusion kernel sparse preserving projection(MSFKSPP) ba...In order to extract the richer feature information of ship targets from sea clutter, and address the high dimensional data problem, a method termed as multi-scale fusion kernel sparse preserving projection(MSFKSPP) based on the maximum margin criterion(MMC) is proposed for recognizing the class of ship targets utilizing the high-resolution range profile(HRRP). Multi-scale fusion is introduced to capture the local and detailed information in small-scale features, and the global and contour information in large-scale features, offering help to extract the edge information from sea clutter and further improving the target recognition accuracy. The proposed method can maximally preserve the multi-scale fusion sparse of data and maximize the class separability in the reduced dimensionality by reproducing kernel Hilbert space. Experimental results on the measured radar data show that the proposed method can effectively extract the features of ship target from sea clutter, further reduce the feature dimensionality, and improve target recognition performance.展开更多
In this paper,we introduce an incident angle based fusion method for radar and infrared sensors to improve the recognition rate of complex targets under half space scenarios,e.g.,vehicles on the ground in this paper.F...In this paper,we introduce an incident angle based fusion method for radar and infrared sensors to improve the recognition rate of complex targets under half space scenarios,e.g.,vehicles on the ground in this paper.For radar sensors,convolutional operation is introduced into the autoencoder,a“winner-take-all(WTA)”convolutional autoencoder(CAE)is used to improve the recognition rate of the radar high resolution range profile(HRRP).Moreover,different from the free space,the HRRP in half space is more complex.In order to get closer to the real situation,the half space HRRP is simulated as the dataset.The recognition rate has a growth more than 7%com-pared with the traditional CAE or denoised sparse autoencoder(DSAE).For infrared sensor,a convolutional neural network(CNN)is used for infrared image recognition.Finally,we com-bine the two results with the Dempster-Shafer(D-S)evidence theory,and the discounting operation is introduced in the fusion to improve the recognition rate.The recognition rate after fusion has a growth more than 7%compared with a single sensor.After the discounting operation,the accuracy rate has been improved by 1.5%,which validates the effectiveness of the proposed method.展开更多
当前射电望远镜台址射频干扰越来越多,需尽量找到射频干扰源并予以消减。无线定位技术是查找干扰源、获取射频发射源准确位置的重要技术手段。基于测距的无线定位算法因其定位精度高、稳定性强而备受关注。对几种基于测距的无线定位算...当前射电望远镜台址射频干扰越来越多,需尽量找到射频干扰源并予以消减。无线定位技术是查找干扰源、获取射频发射源准确位置的重要技术手段。基于测距的无线定位算法因其定位精度高、稳定性强而备受关注。对几种基于测距的无线定位算法进行研究,分析对比这几种测距定位算法的特点。通过对比,基于到达时间差(Time Difference of Arrival,TDOA)定位算法的计算复杂度低,定位精度高;基于接收信号强度(Received Signal Strength Indication,RSSI)定位算法简单易于实现。在此基础上提出了一种基于到达时间差定位算法和基于接收信号强度定位算法数据融合的测距无线定位算法,该算法在通过基于到达时间差定位算法获得多个初始位置估计值的基础上,引入以信号接收强度作为初始位置估计值的权值的数据融合方式,通过线性加权归一化处理获得一个定位精度较高的位置估计值。因信号接收强度易于获得,该数据融合算法在基于到达时间差定位算法基础上增加的计算量较小,仿真结果表明,该算法比单一的基于到达时间差定位算法降低了约20%的定位误差,有效提高了定位精度,便于快速发现射频干扰源。展开更多
In this paper, we take the model of Laser range finder based on synchronized scanner as example, show how to use data fusion method in the process of sensor model designing to get more robust output. Also we provide o...In this paper, we take the model of Laser range finder based on synchronized scanner as example, show how to use data fusion method in the process of sensor model designing to get more robust output. Also we provide our idea on the relation of sensor model, data fusion and system structure, and in the paper, there is a solution that transform the parameter space to get linear model for Kalman filter.展开更多
Background: Multiple level anterior cervical discectomy and fusion (ACDF) is indicated for those who suffer from multilevel stenosis or compression of the spinal canal. It was reported that this intervention would unf...Background: Multiple level anterior cervical discectomy and fusion (ACDF) is indicated for those who suffer from multilevel stenosis or compression of the spinal canal. It was reported that this intervention would unfortunately lead to a loss of normal cervical range of motion (CROM). Although, fewer studies have demonstrated the exact impact of the procedure on CROM. In our study, short and midterm postoperative CROM was described. Methods: Ninety patients who underwent ACDF were followed up postoperatively for at least 3 months. Active CROM was measured in all patients preoperatively and in postoperative follow-ups by cervical spine X-rays in lateral dynamic view using Cobb’s angle method. Results: Unfortunately, postoperative CROM was significantly diminished. At the short-term (3 months) follow-up there was a great limitation in CROM. While an obvious increase in CROM at the midterm (6 months) follow-up was observed in flexion especially. The reduction in global ROM (calculated as preoperative global ROM – 6 months postoperative ROM) was 4.1 and the reduction rate (calculated as reduction ROM divided by preoperative ROM) was 9.5%. The recovery ROM (calculated as 6 months postoperative ROM – 1 month postoperative ROM) was 8.2. The recovery rate (calculated as recovery ROM divided by 1 month postoperative ROM) was 26.5%. Conclusion: Active CROM following multiple level ACDF was obviously diminished. The most affected motion after surgery was flexion. It was noticed that at the short-term follow-up CROM would be more limited while after further follow up CROM was obviously improved even in neck flexion motion.展开更多
基金This work was supported by the National Natural Science Foundation of China(62075169,62003247,62061160370)the Key Research and Development Program of Hubei Province(2020BAB113).
文摘This study proposes a novel general image fusion framework based on cross-domain long-range learning and Swin Transformer,termed as SwinFusion.On the one hand,an attention-guided cross-domain module is devised to achieve sufficient integration of complementary information and global interaction.More specifically,the proposed method involves an intra-domain fusion unit based on self-attention and an interdomain fusion unit based on cross-attention,which mine and integrate long dependencies within the same domain and across domains.Through long-range dependency modeling,the network is able to fully implement domain-specific information extraction and cross-domain complementary information integration as well as maintaining the appropriate apparent intensity from a global perspective.In particular,we introduce the shifted windows mechanism into the self-attention and cross-attention,which allows our model to receive images with arbitrary sizes.On the other hand,the multi-scene image fusion problems are generalized to a unified framework with structure maintenance,detail preservation,and proper intensity control.Moreover,an elaborate loss function,consisting of SSIM loss,texture loss,and intensity loss,drives the network to preserve abundant texture details and structural information,as well as presenting optimal apparent intensity.Extensive experiments on both multi-modal image fusion and digital photography image fusion demonstrate the superiority of our SwinFusion compared to the state-of-theart unified image fusion algorithms and task-specific alternatives.Implementation code and pre-trained weights can be accessed at https://github.com/Linfeng-Tang/SwinFusion.
基金Supported by the Freie und Hansestadt Hamburg and the Bundesministcrium für Gesundheit und Soziale Sicherung grants from DFG and by the German Competence Network for Viral Hepatitis （Hop-Net）, funded by the German Ministry of Education and Research （BMBF）, Grant No. TFI3. IWe apologize to those authors whose work we could not cite directly due to space limitations. The authors are indebted to Claudia Franke （Heinrich-Pette-Institute, Hamburg, Germany） for providing the picture of core protein phosphorylation.
文摘The human hepatitis B virus （HBV） and the duck hepatitis B virus （DHBV） share several fundamental features. Both viruses have a partially double-stranded DNA genome that is replicated via a RNA intermediate and the coding open reading frames （ORFs） overlap extensively. In addition, the genomic and structural organization, as well as replication and biological characteristics, are very similar in both viruses. Host of the key features of hepadnaviral infection were first discovered in the DHBV model system and subsequently confirmed for HBV. There are, however, several differences between human HBV and DHBV. This review will focus on the molecular and cellular biology, evolution, and host adaptation of the avian hepatitis B viruses with particular emphasis on DHBV as a model system.
基金supported by the National Natural Science Foundation of China (60574022).
文摘A new distributed fusion method of radar/infrared （IR） tracking system based on separation and combination of the measurements is proposed by analyzing the influence of rate measurement. The rate information separated from the radar measurements together with measurements of IR form a pseudo vector of IR, and the corresponding filter is designed. The results indicate that the method not only makes a great improvement to the local tracker＇s performance, but also improves the global tracking precision efficiently.
文摘Background Lumbar pedicle screw fixation and fusion are major procedures for treating discogenic low back pain （DLBP）. However, due to its advantages of preserving the segmental motion and biomechanical simulation, artificial total lumbar disc replacement （TDR） is increasingly popular. Methods From 2007 to 2010, 68 DLBP patients were enrolled. TDR were performed on 34 patients and the other 34 controls underwent the traditional fixation procedure. Qualitative and quantitative evaluations were followed including the changes in range of motion （ROM） and interpedicle height （IPH） at the posterior intervertebral body of operated level, in 6 and 12 months, and 3 years, postoperatively. Results Qualitative results showed satisfying improvement in the two groups after 6 and 12 months, respectively, and the inter-group differences were significant （P 〉0.05）. The results of ROM and IPH have shown significant differences between the TDR and spinal fusion groups （P 〈0.05）. Conclusion With similar clinical improvements as the traditional spinal fusion method, TDR offered significantly better ROM and intervertebral foramen hei.qht.
基金supported by the National Natural Science Foundation of China (62271255,61871218)the Fundamental Research Funds for the Central University (3082019NC2019002)+1 种基金the Aeronautical Science Foundation (ASFC-201920007002)the Program of Remote Sensing Intelligent Monitoring and Emergency Services for Regional Security Elements。
文摘In order to extract the richer feature information of ship targets from sea clutter, and address the high dimensional data problem, a method termed as multi-scale fusion kernel sparse preserving projection(MSFKSPP) based on the maximum margin criterion(MMC) is proposed for recognizing the class of ship targets utilizing the high-resolution range profile(HRRP). Multi-scale fusion is introduced to capture the local and detailed information in small-scale features, and the global and contour information in large-scale features, offering help to extract the edge information from sea clutter and further improving the target recognition accuracy. The proposed method can maximally preserve the multi-scale fusion sparse of data and maximize the class separability in the reduced dimensionality by reproducing kernel Hilbert space. Experimental results on the measured radar data show that the proposed method can effectively extract the features of ship target from sea clutter, further reduce the feature dimensionality, and improve target recognition performance.
基金supported by the National Natural Science Foundation of China(61571022,61971022).
文摘In this paper,we introduce an incident angle based fusion method for radar and infrared sensors to improve the recognition rate of complex targets under half space scenarios,e.g.,vehicles on the ground in this paper.For radar sensors,convolutional operation is introduced into the autoencoder,a“winner-take-all(WTA)”convolutional autoencoder(CAE)is used to improve the recognition rate of the radar high resolution range profile(HRRP).Moreover,different from the free space,the HRRP in half space is more complex.In order to get closer to the real situation,the half space HRRP is simulated as the dataset.The recognition rate has a growth more than 7%com-pared with the traditional CAE or denoised sparse autoencoder(DSAE).For infrared sensor,a convolutional neural network(CNN)is used for infrared image recognition.Finally,we com-bine the two results with the Dempster-Shafer(D-S)evidence theory,and the discounting operation is introduced in the fusion to improve the recognition rate.The recognition rate after fusion has a growth more than 7%compared with a single sensor.After the discounting operation,the accuracy rate has been improved by 1.5%,which validates the effectiveness of the proposed method.
文摘当前射电望远镜台址射频干扰越来越多,需尽量找到射频干扰源并予以消减。无线定位技术是查找干扰源、获取射频发射源准确位置的重要技术手段。基于测距的无线定位算法因其定位精度高、稳定性强而备受关注。对几种基于测距的无线定位算法进行研究,分析对比这几种测距定位算法的特点。通过对比,基于到达时间差(Time Difference of Arrival,TDOA)定位算法的计算复杂度低,定位精度高;基于接收信号强度(Received Signal Strength Indication,RSSI)定位算法简单易于实现。在此基础上提出了一种基于到达时间差定位算法和基于接收信号强度定位算法数据融合的测距无线定位算法,该算法在通过基于到达时间差定位算法获得多个初始位置估计值的基础上,引入以信号接收强度作为初始位置估计值的权值的数据融合方式,通过线性加权归一化处理获得一个定位精度较高的位置估计值。因信号接收强度易于获得,该数据融合算法在基于到达时间差定位算法基础上增加的计算量较小,仿真结果表明,该算法比单一的基于到达时间差定位算法降低了约20%的定位误差,有效提高了定位精度,便于快速发现射频干扰源。
文摘In this paper, we take the model of Laser range finder based on synchronized scanner as example, show how to use data fusion method in the process of sensor model designing to get more robust output. Also we provide our idea on the relation of sensor model, data fusion and system structure, and in the paper, there is a solution that transform the parameter space to get linear model for Kalman filter.
文摘Background: Multiple level anterior cervical discectomy and fusion (ACDF) is indicated for those who suffer from multilevel stenosis or compression of the spinal canal. It was reported that this intervention would unfortunately lead to a loss of normal cervical range of motion (CROM). Although, fewer studies have demonstrated the exact impact of the procedure on CROM. In our study, short and midterm postoperative CROM was described. Methods: Ninety patients who underwent ACDF were followed up postoperatively for at least 3 months. Active CROM was measured in all patients preoperatively and in postoperative follow-ups by cervical spine X-rays in lateral dynamic view using Cobb’s angle method. Results: Unfortunately, postoperative CROM was significantly diminished. At the short-term (3 months) follow-up there was a great limitation in CROM. While an obvious increase in CROM at the midterm (6 months) follow-up was observed in flexion especially. The reduction in global ROM (calculated as preoperative global ROM – 6 months postoperative ROM) was 4.1 and the reduction rate (calculated as reduction ROM divided by preoperative ROM) was 9.5%. The recovery ROM (calculated as 6 months postoperative ROM – 1 month postoperative ROM) was 8.2. The recovery rate (calculated as recovery ROM divided by 1 month postoperative ROM) was 26.5%. Conclusion: Active CROM following multiple level ACDF was obviously diminished. The most affected motion after surgery was flexion. It was noticed that at the short-term follow-up CROM would be more limited while after further follow up CROM was obviously improved even in neck flexion motion.
