Change detection(CD)is becoming indispensable for unmanned aerial vehicles(UAVs),especially in the domain of water landing,rescue and search.However,even the most advanced models require large amounts of data for mode...Change detection(CD)is becoming indispensable for unmanned aerial vehicles(UAVs),especially in the domain of water landing,rescue and search.However,even the most advanced models require large amounts of data for model training and testing.Therefore,sufficient labeled images with different imaging conditions are needed.Inspired by computer graphics,we present a cloning method to simulate inland-water scene and collect an auto-labeled simulated dataset.The simulated dataset consists of six challenges to test the effects of dynamic background,weather,and noise on change detection models.Then,we propose an image translation framework that translates simulated images to synthetic images.This framework uses shared parameters(encoder and generator)and 22×22 receptive fields(discriminator)to generate realistic synthetic images as model training sets.The experimental results indicate that:1)different imaging challenges affect the performance of change detection models;2)compared with simulated images,synthetic images can effectively improve the accuracy of supervised models.展开更多
Through analyzing the different height parameter of 3D surface between the artificial target and complex background based on the description of average Holder constant of fractional Brownian motion, a novel method of ...Through analyzing the different height parameter of 3D surface between the artificial target and complex background based on the description of average Holder constant of fractional Brownian motion, a novel method of target detection based on wavelet transformation and Holder constant is proposed. The wavelet Holder constants are calculated and linearly interpolated in a series of images, the target is detected by testing the linearity errof The more accurate localization can be achieved using two images of the same region but with difIerent scaling parameters.The application results of this algorithm for target detection are also given, and show that this method has good performance of noise immunity. This method is also suitable for identifying specific targets in complex background.展开更多
Supervised models for event detection usually require large-scale human-annotated training data,especially neural models.A data augmentation technique is proposed to improve the performance of event detection by gener...Supervised models for event detection usually require large-scale human-annotated training data,especially neural models.A data augmentation technique is proposed to improve the performance of event detection by generating paraphrase sentences to enrich expressions of the original data.Specifically,based on an existing human-annotated event detection dataset,we first automatically build a paraphrase dataset and label it with a designed event annotation alignment algorithm.To alleviate possible wrong labels in the generated paraphrase dataset,a multi-instance learning(MIL)method is adopted for joint training on both the gold human-annotated data and the generated paraphrase dataset.Experimental results on a widely used dataset ACE2005 show the effectiveness of our approach.展开更多
Gastric cancer(GC)is one of the most common and deadly cancers worldwide.Early detection offers the best chance for curative treatment and reducing its mortality.However,the optimal population-based early screening fo...Gastric cancer(GC)is one of the most common and deadly cancers worldwide.Early detection offers the best chance for curative treatment and reducing its mortality.However,the optimal population-based early screening for GC remains unmet.Aberrant DNA methylation occurs in the early stage of GC,exhibiting cancer-specific genetic and epigenetic changes,and can be detected in the media such as blood,gastric juice,and feces,constituting a valuable biomarker for cancer early detection.Furthermore,DNA methylation is a stable epigenetic alteration,and many innovative methods have been developed to quantify it rapidly and accurately.Nonetheless,large-scale clinical validation of DNA methylation serving as tumor biomarkers is still lacking,precluding their implementation in clinical practice.In conclusion,after a critical analysis of the recent existing literature,we summarized the evolving roles of DNA methylation during GC occurrence,expounded the newly discovered noninvasive DNA methylation biomarkers for early detection of GC,and discussed its challenges and prospects in clinical applications.展开更多
Policy conflicts may cause substantial economic losses.Although a large amount of effort has been spent on detecting intra-domain policy conflict,it can not detect conflicts of heterogeneous policies.In this paper,con...Policy conflicts may cause substantial economic losses.Although a large amount of effort has been spent on detecting intra-domain policy conflict,it can not detect conflicts of heterogeneous policies.In this paper,considering background knowledge,we propose a conflict detection mechanism to search and locate conflicts of heterogeneous policies.First,we propose a general access control model to describe authorization mechanisms of cloud service and a translation scheme designed to translate a cloud service policy to an Extensible Access Control Markup Language(XACML)policy.Then the scheme based on Multi-terminal Multi-data-type Interval Decision Diagram(MTMIDD)and Extended MTMIDD(X-MTMIDD)is designed to represent XACML policy and search the conflict among heterogeneous policies.To reduce the rate of false positives,the description logic is used to represent XACML policy and eliminate false conflicts.Experimental results show the efficiency of our scheme.展开更多
针对在动态环境下,传统的同步定位与地图构建(simultaneous localization and mapping,SLAM)框架在动态物体上产生误匹配,导致计算结果不稳定的问题,提出了一种结合深度学习和平移约束的算法。首先,采用无监督的深度估计网络输出运动场...针对在动态环境下,传统的同步定位与地图构建(simultaneous localization and mapping,SLAM)框架在动态物体上产生误匹配,导致计算结果不稳定的问题,提出了一种结合深度学习和平移约束的算法。首先,采用无监督的深度估计网络输出运动场信息,使用目标检测对训练数据进行预处理,以屏蔽场景静止部分对训练的干扰,同时,通过目标检测获得潜在运动对象,并与运动场信息联合判断该目标是否为运动对象。为了进一步剔除异常的匹配点,本文充分利用了直线行驶情况下的先验信息,通过灭点和匹配点对的约束关系,达到剔除异常匹配点的效果。结果表明:该方法较ORB-SLAM2在KITTI、TUM数据集上均方根误差分别降低了约16.38%、84.26%,与DynaSLAM相比降低了约6.65%、8.32%,同时较DynaSLAM效率也有所提升。展开更多
基金supported in part by the Science and Technology Innovation 2030-Key Project of“New Generation Artificial Intelligence”(2018AAA0102303)the Young Elite Scientists Sponsorship Program of China Association of Science and Technology(YESS20210289)+1 种基金the China Postdoctoral Science Foundation(2020TQ1057,2020M682823)the National Natural Science Foundation of China(U20B2071,U1913602,91948204)。
文摘Change detection(CD)is becoming indispensable for unmanned aerial vehicles(UAVs),especially in the domain of water landing,rescue and search.However,even the most advanced models require large amounts of data for model training and testing.Therefore,sufficient labeled images with different imaging conditions are needed.Inspired by computer graphics,we present a cloning method to simulate inland-water scene and collect an auto-labeled simulated dataset.The simulated dataset consists of six challenges to test the effects of dynamic background,weather,and noise on change detection models.Then,we propose an image translation framework that translates simulated images to synthetic images.This framework uses shared parameters(encoder and generator)and 22×22 receptive fields(discriminator)to generate realistic synthetic images as model training sets.The experimental results indicate that:1)different imaging challenges affect the performance of change detection models;2)compared with simulated images,synthetic images can effectively improve the accuracy of supervised models.
基金Supported by the National Natural Science Foundation of China(No.69973018)the Natural Science Foundation of Hubei Province(No.99J009)
文摘Through analyzing the different height parameter of 3D surface between the artificial target and complex background based on the description of average Holder constant of fractional Brownian motion, a novel method of target detection based on wavelet transformation and Holder constant is proposed. The wavelet Holder constants are calculated and linearly interpolated in a series of images, the target is detected by testing the linearity errof The more accurate localization can be achieved using two images of the same region but with difIerent scaling parameters.The application results of this algorithm for target detection are also given, and show that this method has good performance of noise immunity. This method is also suitable for identifying specific targets in complex background.
基金National Natural Science Foundation of China(No.62006039)。
文摘Supervised models for event detection usually require large-scale human-annotated training data,especially neural models.A data augmentation technique is proposed to improve the performance of event detection by generating paraphrase sentences to enrich expressions of the original data.Specifically,based on an existing human-annotated event detection dataset,we first automatically build a paraphrase dataset and label it with a designed event annotation alignment algorithm.To alleviate possible wrong labels in the generated paraphrase dataset,a multi-instance learning(MIL)method is adopted for joint training on both the gold human-annotated data and the generated paraphrase dataset.Experimental results on a widely used dataset ACE2005 show the effectiveness of our approach.
基金supported by the National Natural Science Foundationof China(No.82202611,82202633)China PostdoctoralScience Foundation(No.2022M711912,BX20220194)+2 种基金Natural Science Foundation of Shandong Province,China(No.ZR2022QH031)Natural Science Foundation of Jiangsu Province,China(No.BK20220271)Fundamental Research Funds of the Second Hospital of Shandong University,Shandong,China(No.2022YP01).
文摘Gastric cancer(GC)is one of the most common and deadly cancers worldwide.Early detection offers the best chance for curative treatment and reducing its mortality.However,the optimal population-based early screening for GC remains unmet.Aberrant DNA methylation occurs in the early stage of GC,exhibiting cancer-specific genetic and epigenetic changes,and can be detected in the media such as blood,gastric juice,and feces,constituting a valuable biomarker for cancer early detection.Furthermore,DNA methylation is a stable epigenetic alteration,and many innovative methods have been developed to quantify it rapidly and accurately.Nonetheless,large-scale clinical validation of DNA methylation serving as tumor biomarkers is still lacking,precluding their implementation in clinical practice.In conclusion,after a critical analysis of the recent existing literature,we summarized the evolving roles of DNA methylation during GC occurrence,expounded the newly discovered noninvasive DNA methylation biomarkers for early detection of GC,and discussed its challenges and prospects in clinical applications.
基金This work has been funded by the National Natural Science Foundation of China(No.U1836203)the Shandong Provincial Key Research and Development Program(2019JZZY20127).
文摘Policy conflicts may cause substantial economic losses.Although a large amount of effort has been spent on detecting intra-domain policy conflict,it can not detect conflicts of heterogeneous policies.In this paper,considering background knowledge,we propose a conflict detection mechanism to search and locate conflicts of heterogeneous policies.First,we propose a general access control model to describe authorization mechanisms of cloud service and a translation scheme designed to translate a cloud service policy to an Extensible Access Control Markup Language(XACML)policy.Then the scheme based on Multi-terminal Multi-data-type Interval Decision Diagram(MTMIDD)and Extended MTMIDD(X-MTMIDD)is designed to represent XACML policy and search the conflict among heterogeneous policies.To reduce the rate of false positives,the description logic is used to represent XACML policy and eliminate false conflicts.Experimental results show the efficiency of our scheme.
文摘针对在动态环境下,传统的同步定位与地图构建(simultaneous localization and mapping,SLAM)框架在动态物体上产生误匹配,导致计算结果不稳定的问题,提出了一种结合深度学习和平移约束的算法。首先,采用无监督的深度估计网络输出运动场信息,使用目标检测对训练数据进行预处理,以屏蔽场景静止部分对训练的干扰,同时,通过目标检测获得潜在运动对象,并与运动场信息联合判断该目标是否为运动对象。为了进一步剔除异常的匹配点,本文充分利用了直线行驶情况下的先验信息,通过灭点和匹配点对的约束关系,达到剔除异常匹配点的效果。结果表明:该方法较ORB-SLAM2在KITTI、TUM数据集上均方根误差分别降低了约16.38%、84.26%,与DynaSLAM相比降低了约6.65%、8.32%,同时较DynaSLAM效率也有所提升。
