BACKGROUND Deep learning provides an efficient automatic image recognition method for small bowel(SB)capsule endoscopy(CE)that can assist physicians in diagnosis.However,the existing deep learning models present some ...BACKGROUND Deep learning provides an efficient automatic image recognition method for small bowel(SB)capsule endoscopy(CE)that can assist physicians in diagnosis.However,the existing deep learning models present some unresolved challenges.AIM To propose a novel and effective classification and detection model to automatically identify various SB lesions and their bleeding risks,and label the lesions accurately so as to enhance the diagnostic efficiency of physicians and the ability to identify high-risk bleeding groups.METHODS The proposed model represents a two-stage method that combined image classification with object detection.First,we utilized the improved ResNet-50 classification model to classify endoscopic images into SB lesion images,normal SB mucosa images,and invalid images.Then,the improved YOLO-V5 detection model was utilized to detect the type of lesion and its risk of bleeding,and the location of the lesion was marked.We constructed training and testing sets and compared model-assisted reading with physician reading.RESULTS The accuracy of the model constructed in this study reached 98.96%,which was higher than the accuracy of other systems using only a single module.The sensitivity,specificity,and accuracy of the model-assisted reading detection of all images were 99.17%,99.92%,and 99.86%,which were significantly higher than those of the endoscopists’diagnoses.The image processing time of the model was 48 ms/image,and the image processing time of the physicians was 0.40±0.24 s/image(P<0.001).CONCLUSION The deep learning model of image classification combined with object detection exhibits a satisfactory diagnostic effect on a variety of SB lesions and their bleeding risks in CE images,which enhances the diagnostic efficiency of physicians and improves the ability of physicians to identify high-risk bleeding groups.展开更多
在“碳达峰、碳中和”背景下,新能源发电逐渐占主导地位,电动汽车数量增长显著,电动汽车光伏充电站将在需求响应方面有重要作用。该文提出一种天气影响下基于风险评估的电动汽车光伏充电站的需求响应方案,根据构建的“预测—预防—响应...在“碳达峰、碳中和”背景下,新能源发电逐渐占主导地位,电动汽车数量增长显著,电动汽车光伏充电站将在需求响应方面有重要作用。该文提出一种天气影响下基于风险评估的电动汽车光伏充电站的需求响应方案,根据构建的“预测—预防—响应”三阶段流程图,结合电网及天气的地理信息系统(geographic information system,GIS)数据进行多层时空数据整合分析,作出风险地图;并据此进行天气对用户影响的风险评估,对装备有光伏发电的电动汽车充电站的运行成本进行建模,优化充电站资源在日前储备市场的参与方案;在用户参与下分别进行需求侧管理(demand side management,DSM)和停电应急管理(outage management,OM),并进行案例研究。该文研究能有效预测天气对电力用户影响并将其可视化,并验证了带有光伏发电的电动汽车充电站,有助于减轻天气对电力供应造成负面影响的作用。展开更多
BACKGROUND While colorectal polyps are not cancerous,some types of polyps,known as adenomas,can develop into colorectal cancer over time.Polyps can often be found and removed by colonoscopy;however,this is an invasive...BACKGROUND While colorectal polyps are not cancerous,some types of polyps,known as adenomas,can develop into colorectal cancer over time.Polyps can often be found and removed by colonoscopy;however,this is an invasive and expensive test.Thus,there is a need for new methods of screening patients at high risk of developing polyps.AIM To identify a potential association between colorectal polyps and small intestine bacteria overgrowth(SIBO)or other relevant factors in a patient cohort with lactulose breath test(LBT)results.METHODS A total of 382 patients who had received an LBT were classified into polyp and non-polyp groups that were confirmed by colonoscopy and pathology.SIBO was diagnosed by measuring LBTderived hydrogen(H)and methane(M)levels according to 2017 North American Consensus recommendations.Logistic regression was used to assess the ability of LBT to predict colorectal polyps.Intestinal barrier function damage(IBFD)was determined by blood assays.RESULTS H and M levels revealed that the prevalence of SIBO was significantly higher in the polyp group than in the non-polyp group(41%vs 23%,P<0.01;71%vs 59%,P<0.05,respectively).Within 90 min of lactulose ingestion,the peak H values in the adenomatous and inflammatory/hyperplastic polyp patients were significantly higher than those in the non-polyp group(P<0.01,and P=0.03,respectively).In 227 patients with SIBO defined by combining H and M values,the rate of IBFD determined by blood lipopolysaccharide levels was significantly higher among patients with polyps than those without(15%vs 5%,P<0.05).In regression analysis with age and gender adjustment,colorectal polyps were most accurately predicted with models using M peak values or combined H and M values limited by North American Consensus recommendations for SIBO.These models had a sensitivity of≥0.67,a specificity of≥0.64,and an accuracy of≥0.66.CONCLUSION The current study made key associations among colorectal polyps,SIBO,and IBFD and demonstrated that LBT has moderate potential as an alternative noninvasive screening tool for colorectal polyps.展开更多
有限状态集模型预测控制具备快速动态响应、无调制模块等优势,已在高性能功率变换器广泛应用。然而该技术高度依赖建模精度,实际应用中受模型匹配度和参数摄动等因素影响,难以运行于最优性能。为此,提出一种基于递归最小二乘(recursive ...有限状态集模型预测控制具备快速动态响应、无调制模块等优势,已在高性能功率变换器广泛应用。然而该技术高度依赖建模精度,实际应用中受模型匹配度和参数摄动等因素影响,难以运行于最优性能。为此,提出一种基于递归最小二乘(recursive least squares,RLS)估算的无参数预测控制方法。以数据驱动建模代替物理参数建模,首先采用外生变量自回归技术建立三相逆变器等效模型,并利用RLS算法进行等效模型参数估算。最后,基于22 kW测试平台对所提方法进行验证与分析。结果表明,所提方法对模型和参数变化具有强鲁棒性,不失为一种通用型鲁棒预测控制方案。展开更多
Objective C-reactive protein(CRP)/albumin ratio(CAR)is a new inflammation-based index for predicting the prognosis of various diseases.The CAR determined on admission may help to predict the prognostic value of multip...Objective C-reactive protein(CRP)/albumin ratio(CAR)is a new inflammation-based index for predicting the prognosis of various diseases.The CAR determined on admission may help to predict the prognostic value of multiple trauma patients.Methods A total of 264 adult patients with severe multiple trauma were included for the present retrospective study,together with the collection of relevant clinical and laboratory data.CAR,CRP,albumin,shock index and ISS were incorporated into the prognostic model,and the receiver operating characteristic(ROC)curve was drawn.Then,the shock index for patients with different levels of CAR was analyzed.Finally,univariate and multivariate logistic regression analyses were performed to identify the independent risk factors for the 28-day mortality of multiple trauma patients.Results A total of 36 patients had poor survival outcomes,and the mortality rate reached 13.6%.Furthermore,after analyzing the shock index for patients with different levels of CAR,it was revealed that the shock index was significantly higher when CAR was≥4,when compared to CAR<2 and 2≤CAR<4,in multiple trauma patients.The multivariate logistic analysis helped to identify the independent association between the variables CAR(P=0.029)and shock index(P=0.019),and the 28-day mortality of multiple trauma patients.Conclusion CAR is higher in patients with severe multiple trauma.Furthermore,CAR serves as a risk factor for independently predicting the 28-day mortality of multiple trauma patients.The shock index was significantly higher when CAR was≥4 in multiple trauma patients.展开更多
Dear Editor,Dummy attack(DA), a deep stealthy but impactful data integrity attack on power industrial control processes, is recently recognized as hiding the corrupted measurements in normal measurements. In this lett...Dear Editor,Dummy attack(DA), a deep stealthy but impactful data integrity attack on power industrial control processes, is recently recognized as hiding the corrupted measurements in normal measurements. In this letter, targeting a more practical case, we aim to detect the oneshot DA, with the purpose of revealing the DA once it is launched.Specifically, we first formulate an optimization problem to generate one-shot DAs. Then, an unsupervised data-driven approach based on a modified local outlier factor(MLOF) is proposed to detect them.展开更多
基金The Shanxi Provincial Administration of Traditional Chinese Medicine,No.2023ZYYDA2005.
文摘BACKGROUND Deep learning provides an efficient automatic image recognition method for small bowel(SB)capsule endoscopy(CE)that can assist physicians in diagnosis.However,the existing deep learning models present some unresolved challenges.AIM To propose a novel and effective classification and detection model to automatically identify various SB lesions and their bleeding risks,and label the lesions accurately so as to enhance the diagnostic efficiency of physicians and the ability to identify high-risk bleeding groups.METHODS The proposed model represents a two-stage method that combined image classification with object detection.First,we utilized the improved ResNet-50 classification model to classify endoscopic images into SB lesion images,normal SB mucosa images,and invalid images.Then,the improved YOLO-V5 detection model was utilized to detect the type of lesion and its risk of bleeding,and the location of the lesion was marked.We constructed training and testing sets and compared model-assisted reading with physician reading.RESULTS The accuracy of the model constructed in this study reached 98.96%,which was higher than the accuracy of other systems using only a single module.The sensitivity,specificity,and accuracy of the model-assisted reading detection of all images were 99.17%,99.92%,and 99.86%,which were significantly higher than those of the endoscopists’diagnoses.The image processing time of the model was 48 ms/image,and the image processing time of the physicians was 0.40±0.24 s/image(P<0.001).CONCLUSION The deep learning model of image classification combined with object detection exhibits a satisfactory diagnostic effect on a variety of SB lesions and their bleeding risks in CE images,which enhances the diagnostic efficiency of physicians and improves the ability of physicians to identify high-risk bleeding groups.
文摘在“碳达峰、碳中和”背景下,新能源发电逐渐占主导地位,电动汽车数量增长显著,电动汽车光伏充电站将在需求响应方面有重要作用。该文提出一种天气影响下基于风险评估的电动汽车光伏充电站的需求响应方案,根据构建的“预测—预防—响应”三阶段流程图,结合电网及天气的地理信息系统(geographic information system,GIS)数据进行多层时空数据整合分析,作出风险地图;并据此进行天气对用户影响的风险评估,对装备有光伏发电的电动汽车充电站的运行成本进行建模,优化充电站资源在日前储备市场的参与方案;在用户参与下分别进行需求侧管理(demand side management,DSM)和停电应急管理(outage management,OM),并进行案例研究。该文研究能有效预测天气对电力用户影响并将其可视化,并验证了带有光伏发电的电动汽车充电站,有助于减轻天气对电力供应造成负面影响的作用。
基金Supported by the Key-Area Research and Development Program of Guangdong Province,No.2022B1111070006the Guangdong Innovation Research Team for Higher Education,No.2021KCXTD025.
文摘BACKGROUND While colorectal polyps are not cancerous,some types of polyps,known as adenomas,can develop into colorectal cancer over time.Polyps can often be found and removed by colonoscopy;however,this is an invasive and expensive test.Thus,there is a need for new methods of screening patients at high risk of developing polyps.AIM To identify a potential association between colorectal polyps and small intestine bacteria overgrowth(SIBO)or other relevant factors in a patient cohort with lactulose breath test(LBT)results.METHODS A total of 382 patients who had received an LBT were classified into polyp and non-polyp groups that were confirmed by colonoscopy and pathology.SIBO was diagnosed by measuring LBTderived hydrogen(H)and methane(M)levels according to 2017 North American Consensus recommendations.Logistic regression was used to assess the ability of LBT to predict colorectal polyps.Intestinal barrier function damage(IBFD)was determined by blood assays.RESULTS H and M levels revealed that the prevalence of SIBO was significantly higher in the polyp group than in the non-polyp group(41%vs 23%,P<0.01;71%vs 59%,P<0.05,respectively).Within 90 min of lactulose ingestion,the peak H values in the adenomatous and inflammatory/hyperplastic polyp patients were significantly higher than those in the non-polyp group(P<0.01,and P=0.03,respectively).In 227 patients with SIBO defined by combining H and M values,the rate of IBFD determined by blood lipopolysaccharide levels was significantly higher among patients with polyps than those without(15%vs 5%,P<0.05).In regression analysis with age and gender adjustment,colorectal polyps were most accurately predicted with models using M peak values or combined H and M values limited by North American Consensus recommendations for SIBO.These models had a sensitivity of≥0.67,a specificity of≥0.64,and an accuracy of≥0.66.CONCLUSION The current study made key associations among colorectal polyps,SIBO,and IBFD and demonstrated that LBT has moderate potential as an alternative noninvasive screening tool for colorectal polyps.
文摘有限状态集模型预测控制具备快速动态响应、无调制模块等优势,已在高性能功率变换器广泛应用。然而该技术高度依赖建模精度,实际应用中受模型匹配度和参数摄动等因素影响,难以运行于最优性能。为此,提出一种基于递归最小二乘(recursive least squares,RLS)估算的无参数预测控制方法。以数据驱动建模代替物理参数建模,首先采用外生变量自回归技术建立三相逆变器等效模型,并利用RLS算法进行等效模型参数估算。最后,基于22 kW测试平台对所提方法进行验证与分析。结果表明,所提方法对模型和参数变化具有强鲁棒性,不失为一种通用型鲁棒预测控制方案。
基金supported by Jiangsu Provincial Medical Innovation Center of Jiangsu Province Capability Improvement Project through Science,Technology and Education(No.CXZX202231)the Special Research Topic on Innovation of Hospital Management,Jiangsu Provincial Hospital Association(No.JSYGY-3-2021-JZ71).
文摘Objective C-reactive protein(CRP)/albumin ratio(CAR)is a new inflammation-based index for predicting the prognosis of various diseases.The CAR determined on admission may help to predict the prognostic value of multiple trauma patients.Methods A total of 264 adult patients with severe multiple trauma were included for the present retrospective study,together with the collection of relevant clinical and laboratory data.CAR,CRP,albumin,shock index and ISS were incorporated into the prognostic model,and the receiver operating characteristic(ROC)curve was drawn.Then,the shock index for patients with different levels of CAR was analyzed.Finally,univariate and multivariate logistic regression analyses were performed to identify the independent risk factors for the 28-day mortality of multiple trauma patients.Results A total of 36 patients had poor survival outcomes,and the mortality rate reached 13.6%.Furthermore,after analyzing the shock index for patients with different levels of CAR,it was revealed that the shock index was significantly higher when CAR was≥4,when compared to CAR<2 and 2≤CAR<4,in multiple trauma patients.The multivariate logistic analysis helped to identify the independent association between the variables CAR(P=0.029)and shock index(P=0.019),and the 28-day mortality of multiple trauma patients.Conclusion CAR is higher in patients with severe multiple trauma.Furthermore,CAR serves as a risk factor for independently predicting the 28-day mortality of multiple trauma patients.The shock index was significantly higher when CAR was≥4 in multiple trauma patients.
基金supported in part by the Guizhou Provincial Science and Technology Projects(ZK[2022]149)the Guizhou Provincial Research Project for Universities([2022]104)+2 种基金the Special Foundation of Guizhou University([2021]47)the GZU cultivation project of National Natural Science Foundation of China([2020]80)Shanghai Engineering Research Center of Big Data Management,and the National Natural Science Foundation of China(62073285,62061130220)。
文摘Dear Editor,Dummy attack(DA), a deep stealthy but impactful data integrity attack on power industrial control processes, is recently recognized as hiding the corrupted measurements in normal measurements. In this letter, targeting a more practical case, we aim to detect the oneshot DA, with the purpose of revealing the DA once it is launched.Specifically, we first formulate an optimization problem to generate one-shot DAs. Then, an unsupervised data-driven approach based on a modified local outlier factor(MLOF) is proposed to detect them.
