Tuna is superior among the marine fishes that are exported in the forms of raw fish and processed food.Separation of Tuna into their species is done in industries manually,and the process is tiresome.This work propose...Tuna is superior among the marine fishes that are exported in the forms of raw fish and processed food.Separation of Tuna into their species is done in industries manually,and the process is tiresome.This work proposes an automated system for classifying Tuna spe-cies based on their images.An ensemble of region-based deep neural networks is used.A sub region contrast stretching operation is applied to enhance the images.Each fish image is then divided into three regions and is augmented before giving as input to pre-trained convolutional neural networks(CNN).After fine-tuning the models,the output from the last convolutional layer is given to a grouped 2D-local binary pattern descriptor(G2DLBP).Statistical features from the descriptor are applied to different classifiers,and the best clas-sifier for each image region model is identified.Different ensemble methods are subse-quently used to combine the three CNN-G2DLBP models.Among the ensemble techniques,super learner ensemble method with random forest(RF)classifier using 5-fold cross-validation shows the highest classification accuracy of 97.32%.The perfor-mance of different ensemble methods is analyzed in terms of accuracy,precision,recall,and f-score.The proposed system shows an accuracy of 93.91% when evaluated with an independent test dataset.An ensemble of region-based CNN with textural features from G2DLBP is applied for the first time for fish classification.展开更多
目的系统阐述靶向最大似然估计(targeted maximum likelihood estimation,TMLE)的基本原理和实施流程,为观察性研究的因果推断问题提供方法学指导。方法基于Diabetes数据集构建模拟数据,设置正确设定和双重误设两类情景,分别采用传统方...目的系统阐述靶向最大似然估计(targeted maximum likelihood estimation,TMLE)的基本原理和实施流程,为观察性研究的因果推断问题提供方法学指导。方法基于Diabetes数据集构建模拟数据,设置正确设定和双重误设两类情景,分别采用传统方法(G计算、逆处理概率加权)、TMLE、TMLE结合超级学习(super learner,SL)估计因果效应的边际比值比(marginal odds ratio,MOR)及其95%CI,并通过偏差、均方误差及95%CI覆盖率评估其性能。进一步基于Lindner数据集分析经皮冠状动脉介入联合阿昔单抗治疗与6个月生存状态之间的关联,以验证该方法在实例数据中的因果推断效果。结果模拟研究表明,在正确设定条件下,所有方法均表现良好;而在双重误设情况下,TMLE及TMLE+SL均表现出较小的偏差(TMLE:0.018;TMLE+SL:0.012)和均方误差(TMLE:0.173;TMLE+SL:0.066),95%CI覆盖率最接近名义水平,均为96.00%,准确性和稳健性优于传统方法。实例分析中,4种方法结果均显示,经皮冠状动脉介入联合阿昔单抗具有保护作用(MOR<1),其中TMLE+SL的95%CI最窄(MOR=0.201,95%CI:0.093~0.436),估计精度最高。结论TMLE,尤其是TMLE+SL,能够有效优化目标参数的偏差-方差权衡,为观察性研究提供更精确且稳健的因果效应估计,具有重要的方法学价值。展开更多
目的依托山东省胶南市“全人群高血压、糖尿病综合防治项目”建立队列,借助靶向最大似然估计(targeted maximum likelihood estimation,TMLE)模型评价高血压患者服用卡托普利或尼群地平对血压控制的平均因果效应和个体化因果效应,在大...目的依托山东省胶南市“全人群高血压、糖尿病综合防治项目”建立队列,借助靶向最大似然估计(targeted maximum likelihood estimation,TMLE)模型评价高血压患者服用卡托普利或尼群地平对血压控制的平均因果效应和个体化因果效应,在大数据背景下辅助精准医疗以实现高血压控制。方法筛选只服用卡托普利或尼群地平的患者,将其第一次随访血压控制情况作为结局,将年龄、性别、职业、BMI、吸烟、饮酒及运动情况纳入分析,采用嵌入Super Learner组合预测算法的靶向最大似然估计模型拟合条件均值结果的初始估计并进行波动,更新初始拟合,对目标参数做出最优偏差-方差权衡优化模型,从而得到平均因果效应,并进一步分析个体化因果效应。结果共纳入13676名高血压患者。总体上相比服用卡托普利,服用尼群地平更有利于血压控制(OR=1.24,95%CI:1.13~1.35,P=0.004)。从个体净效应来看,98.65%的患者使用尼群地平的血压控制效果更好。结论靶向最大似然估计模型能够分析平均因果效应和个性化因果效应,为现实世界的因果推断研究提供方法借鉴。展开更多
文摘Tuna is superior among the marine fishes that are exported in the forms of raw fish and processed food.Separation of Tuna into their species is done in industries manually,and the process is tiresome.This work proposes an automated system for classifying Tuna spe-cies based on their images.An ensemble of region-based deep neural networks is used.A sub region contrast stretching operation is applied to enhance the images.Each fish image is then divided into three regions and is augmented before giving as input to pre-trained convolutional neural networks(CNN).After fine-tuning the models,the output from the last convolutional layer is given to a grouped 2D-local binary pattern descriptor(G2DLBP).Statistical features from the descriptor are applied to different classifiers,and the best clas-sifier for each image region model is identified.Different ensemble methods are subse-quently used to combine the three CNN-G2DLBP models.Among the ensemble techniques,super learner ensemble method with random forest(RF)classifier using 5-fold cross-validation shows the highest classification accuracy of 97.32%.The perfor-mance of different ensemble methods is analyzed in terms of accuracy,precision,recall,and f-score.The proposed system shows an accuracy of 93.91% when evaluated with an independent test dataset.An ensemble of region-based CNN with textural features from G2DLBP is applied for the first time for fish classification.
文摘目的依托山东省胶南市“全人群高血压、糖尿病综合防治项目”建立队列,借助靶向最大似然估计(targeted maximum likelihood estimation,TMLE)模型评价高血压患者服用卡托普利或尼群地平对血压控制的平均因果效应和个体化因果效应,在大数据背景下辅助精准医疗以实现高血压控制。方法筛选只服用卡托普利或尼群地平的患者,将其第一次随访血压控制情况作为结局,将年龄、性别、职业、BMI、吸烟、饮酒及运动情况纳入分析,采用嵌入Super Learner组合预测算法的靶向最大似然估计模型拟合条件均值结果的初始估计并进行波动,更新初始拟合,对目标参数做出最优偏差-方差权衡优化模型,从而得到平均因果效应,并进一步分析个体化因果效应。结果共纳入13676名高血压患者。总体上相比服用卡托普利,服用尼群地平更有利于血压控制(OR=1.24,95%CI:1.13~1.35,P=0.004)。从个体净效应来看,98.65%的患者使用尼群地平的血压控制效果更好。结论靶向最大似然估计模型能够分析平均因果效应和个性化因果效应,为现实世界的因果推断研究提供方法借鉴。
