This study presents an innovative approach to improving the performance of YOLO-v8 model for small object detection in radar images.Initially,a local histogram equalization technique was applied to the original images...This study presents an innovative approach to improving the performance of YOLO-v8 model for small object detection in radar images.Initially,a local histogram equalization technique was applied to the original images,resulting in a notable enhancement in both contrast and detail representation.Subsequently,the YOLO-v8 backbone network was augmented by incorporating convolutional kernels based on a multidimensional attention mechanism and a parallel processing strategy,which facilitated more effective feature information fusion.At the model’s head,an upsampling layer was added,along with the fusion of outputs from the shallow network,and a detection head specifically tailored for small object detection,thereby further improving accuracy.Additionally,the loss function was modified to incorporate focal-intersection over union(IoU)in conjunction with scaled-IoU,which enhanced the model’s performance.A weighting strategy was also introduced,effectively improving detection accuracy for small targets.Experimental results demonstrate that the customized model outperforms traditional approaches across various evaluation metrics,including recall,precision,F1-score,and the receiver operating characteristic(ROC)curve,validating its efficacy and innovation in small object detection within radar imagery.The results indicate a substantial improvement in accuracy compared to conventional methods such as image segmentation and standard convolutional neural networks.展开更多
证据是循证医学的核心要素,其分类多样、来源广泛,大多以学术期刊为载体,收录于PubMed、Web of Science、中国知网等各类数据库或网站平台,载体繁多且数量庞大,给科研工作者查阅文献、阅读文献带来了较大的负担,泌尿外科领域循证证据更...证据是循证医学的核心要素,其分类多样、来源广泛,大多以学术期刊为载体,收录于PubMed、Web of Science、中国知网等各类数据库或网站平台,载体繁多且数量庞大,给科研工作者查阅文献、阅读文献带来了较大的负担,泌尿外科领域循证证据更是如此。本文从分析泌尿外科领域常见临床问题特征入手,介绍了其筛选的4项标准、2类结构化模板,阐明了4种证据分类方法的含义、类别、标识及其方法应用的3项要求,并以生产证据和使用证据为目的的检索思路分别讲解了检索资源的选择、检索策略的构建、检索过程实现的具体操作步骤及其注意事项,另结合人工智能技术,明确了循证泌尿外科领域证据分类和检索的未来发展动向,为进一步推动循证泌尿外科学的发展提供参考依据。展开更多
在当前大数据时代深度学习蓬勃发展,成为解决实际问题的强大工具.然而,传统的集中式深度学习系统存在隐私泄露风险.为解决此问题出现了联邦学习,即一种分布式机器学习方法.联邦学习允许多个机构或个人在不共享原始数据的情况下共同训练...在当前大数据时代深度学习蓬勃发展,成为解决实际问题的强大工具.然而,传统的集中式深度学习系统存在隐私泄露风险.为解决此问题出现了联邦学习,即一种分布式机器学习方法.联邦学习允许多个机构或个人在不共享原始数据的情况下共同训练模型,通过上传本地模型参数至服务器,聚合各用户参数构建全局模型,再返回给用户.这种方法既实现了全局优化,又避免了私有数据泄露.然而,即使采用联邦学习,攻击者仍有可能通过获取用户上传的模型参数还原用户数据,从而侵犯隐私.为解决这一问题,隐私保护成为联邦学习研究的核心,提出了一种基于模分量同态加密的联邦学习(federated learning based on confused modulo projection homomorphic encryption,FLFC)方案.该方案采用自研的模分量全同态加密算法对用户模型参数进行加密,模分量全同态加密算法具有运算效率高、支持浮点数运算、国产化的优点,从而实现了对隐私的更加强大的保护.实验结果表明,FLFC方案在实验中表现出比FedAvg方案更高的平均准确率,且稳定性良好.展开更多
基金supported by the Na‑tional Natural Science Foundation of China Joint Fund(No.U21B2028)the National Key R&D Program of China(No.2021YFC 2100100)the Shanghai Science and Technology Project(Nos.21JC1403400,23JC1402300).
文摘This study presents an innovative approach to improving the performance of YOLO-v8 model for small object detection in radar images.Initially,a local histogram equalization technique was applied to the original images,resulting in a notable enhancement in both contrast and detail representation.Subsequently,the YOLO-v8 backbone network was augmented by incorporating convolutional kernels based on a multidimensional attention mechanism and a parallel processing strategy,which facilitated more effective feature information fusion.At the model’s head,an upsampling layer was added,along with the fusion of outputs from the shallow network,and a detection head specifically tailored for small object detection,thereby further improving accuracy.Additionally,the loss function was modified to incorporate focal-intersection over union(IoU)in conjunction with scaled-IoU,which enhanced the model’s performance.A weighting strategy was also introduced,effectively improving detection accuracy for small targets.Experimental results demonstrate that the customized model outperforms traditional approaches across various evaluation metrics,including recall,precision,F1-score,and the receiver operating characteristic(ROC)curve,validating its efficacy and innovation in small object detection within radar imagery.The results indicate a substantial improvement in accuracy compared to conventional methods such as image segmentation and standard convolutional neural networks.
文摘证据是循证医学的核心要素,其分类多样、来源广泛,大多以学术期刊为载体,收录于PubMed、Web of Science、中国知网等各类数据库或网站平台,载体繁多且数量庞大,给科研工作者查阅文献、阅读文献带来了较大的负担,泌尿外科领域循证证据更是如此。本文从分析泌尿外科领域常见临床问题特征入手,介绍了其筛选的4项标准、2类结构化模板,阐明了4种证据分类方法的含义、类别、标识及其方法应用的3项要求,并以生产证据和使用证据为目的的检索思路分别讲解了检索资源的选择、检索策略的构建、检索过程实现的具体操作步骤及其注意事项,另结合人工智能技术,明确了循证泌尿外科领域证据分类和检索的未来发展动向,为进一步推动循证泌尿外科学的发展提供参考依据。
文摘在当前大数据时代深度学习蓬勃发展,成为解决实际问题的强大工具.然而,传统的集中式深度学习系统存在隐私泄露风险.为解决此问题出现了联邦学习,即一种分布式机器学习方法.联邦学习允许多个机构或个人在不共享原始数据的情况下共同训练模型,通过上传本地模型参数至服务器,聚合各用户参数构建全局模型,再返回给用户.这种方法既实现了全局优化,又避免了私有数据泄露.然而,即使采用联邦学习,攻击者仍有可能通过获取用户上传的模型参数还原用户数据,从而侵犯隐私.为解决这一问题,隐私保护成为联邦学习研究的核心,提出了一种基于模分量同态加密的联邦学习(federated learning based on confused modulo projection homomorphic encryption,FLFC)方案.该方案采用自研的模分量全同态加密算法对用户模型参数进行加密,模分量全同态加密算法具有运算效率高、支持浮点数运算、国产化的优点,从而实现了对隐私的更加强大的保护.实验结果表明,FLFC方案在实验中表现出比FedAvg方案更高的平均准确率,且稳定性良好.
