Heart disease includes a multiplicity of medical conditions that affect the structure,blood vessels,and general operation of the heart.Numerous researchers have made progress in correcting and predicting early heart d...Heart disease includes a multiplicity of medical conditions that affect the structure,blood vessels,and general operation of the heart.Numerous researchers have made progress in correcting and predicting early heart disease,but more remains to be accomplished.The diagnostic accuracy of many current studies is inadequate due to the attempt to predict patients with heart disease using traditional approaches.By using data fusion from several regions of the country,we intend to increase the accuracy of heart disease prediction.A statistical approach that promotes insights triggered by feature interactions to reveal the intricate pattern in the data,which cannot be adequately captured by a single feature.We processed the data using techniques including feature scaling,outlier detection and replacement,null and missing value imputation,and more to improve the data quality.Furthermore,the proposed feature engineering method uses the correlation test for numerical features and the chi-square test for categorical features to interact with the feature.To reduce the dimensionality,we subsequently used PCA with 95%variation.To identify patients with heart disease,hyperparameter-based machine learning algorithms like RF,XGBoost,Gradient Boosting,LightGBM,CatBoost,SVM,and MLP are utilized,along with ensemble models.The model’s overall prediction performance ranges from 88%to 92%.In order to attain cutting-edge results,we then used a 1D CNN model,which significantly enhanced the prediction with an accuracy score of 96.36%,precision of 96.45%,recall of 96.36%,specificity score of 99.51%and F1 score of 96.34%.The RF model produces the best results among all the classifiers in the evaluation matrix without feature interaction,with accuracy of 90.21%,precision of 90.40%,recall of 90.86%,specificity of 90.91%,and F1 score of 90.63%.Our proposed 1D CNN model is 7%superior to the one without feature engineering when compared to the suggested approach.This illustrates how interaction-focused feature analysis can produce precise and useful insights for heart disease diagnosis.展开更多
It aims to draw the conclusion that the ideas of treatment in Zhen Jiu Jia Yi Jing （《针灸甲乙经》, A-B Classic on Acupuncture and Moxibustion ） can be summarized as ＂regulation＂ and ＂harmonization＂ through the ...It aims to draw the conclusion that the ideas of treatment in Zhen Jiu Jia Yi Jing （《针灸甲乙经》, A-B Classic on Acupuncture and Moxibustion ） can be summarized as ＂regulation＂ and ＂harmonization＂ through the research of words in the Classic, such as ＂being normal＂, ＂regulation＂ and ＂harmonization＂. The lost of regulation of a normal person shows disharmony. Regulation can make the person-being-sick become harmony and back to ＂being normal＂. ＂Regulation＂ and ＂harmonization＂ right imply the quintessence of traditional Chinese medicine.展开更多
Quasi-periodic solutions with multiple base frequencies exhibit the feature of 2π-periodicity with respect to each of the hyper-time variables.However,it remains a challenge work,due to the lack of effective solution...Quasi-periodic solutions with multiple base frequencies exhibit the feature of 2π-periodicity with respect to each of the hyper-time variables.However,it remains a challenge work,due to the lack of effective solution methods,to solve and track the quasi-periodic solutions with multiple base frequencies until now.In this work,a multi-steps variable-coefficient formulation is proposed,which provides a unified framework to enable either harmonic balance method or collocation method or finite difference method to solve quasi-periodic solutions with multiple base frequencies.For this purpose,a method of alternating U and S domain is also developed to efficiently evaluate the nonlinear force terms.Furthermore,a new robust phase condition is presented for all of the three methods to make them track the quasi-periodic solutions with prior unknown multiple base frequencies,while the stability of the quasi-periodic solutions is assessed by mean of Lyapunov exponents.The feasibility of the constructed methods under the above framework is verified by application to three nonlinear systems.展开更多
Conventional multilevel inverters often suffer from high harmonic distortion and increased design complexity due to the need for numerous power semiconductor components,particularly at elevated voltage levels.Addressi...Conventional multilevel inverters often suffer from high harmonic distortion and increased design complexity due to the need for numerous power semiconductor components,particularly at elevated voltage levels.Addressing these shortcomings,thiswork presents a robust 15-level PackedUCell(PUC)inverter topology designed for renewable energy and grid-connected applications.The proposed systemintegrates a sensor less proportional-resonant(PR)controller with an advanced carrier-based pulse width modulation scheme.This approach efficiently balances capacitor voltage,minimizes steady-state error,and strongly suppresses both zero and third-order harmonics resulting in reduced total harmonic distortion and enhanced voltage regulation.Additionally,a novel switching algorithm simplifies the design and implementation,further lowering voltage stress across switches.Extensive simulation results validate the performance under various resistive and resistive-inductive load conditions,demonstrating compliance with IEEE-519 THD standards and robust operation under dynamic changes.The proposed sensorless PR-controlled 15-PUC inverter thus offers a compelling,cost-effective solution for efficient power conversion in next-generation renewable energy systems.展开更多
随着电网换相型高压直流输电(line commutated converter based high voltage direct current,LCC-HVDC)技术的广泛应用,交直流混联电网的谐波交互问题愈加复杂,建立LCC-HVDC小信号模型是分析换流器交直流谐波耦合特性的重要手段。为此...随着电网换相型高压直流输电(line commutated converter based high voltage direct current,LCC-HVDC)技术的广泛应用,交直流混联电网的谐波交互问题愈加复杂,建立LCC-HVDC小信号模型是分析换流器交直流谐波耦合特性的重要手段。为此,基于谐波状态空间理论(harmonic state space, HSS)建立双端12脉动LCC-HVDC小信号模型,不仅考虑了LCC谐波传递特性,还考虑了换流变压器联结方式、控制链路延时等因素的影响。采用模块化思想分别建立各子系统谐波状态空间模型,通过接口矩阵连接为整体,使得LCC的谐波状态空间建模在易于扩展的同时,提高了精确度。最后,给出交直流谐波传递的具体表达式,并通过PSCAD仿真验证模型的准确性。所建模型不仅为后续扩展或接入更为复杂的系统奠定了基础,还可应用于双端LCC系统谐波交互稳定性评估和系统参数优化设计。展开更多
本文提出了一种基于调和背景建模的二阶段实例分割方法,可实现复杂遥感图像背景下目标的快速且精细的实例分割。方法包括2个阶段:第1阶段采用可灵活替换的目标检测器,如YOLOv10(You only look once v10)或DINO(DETR with improved denoi...本文提出了一种基于调和背景建模的二阶段实例分割方法,可实现复杂遥感图像背景下目标的快速且精细的实例分割。方法包括2个阶段:第1阶段采用可灵活替换的目标检测器,如YOLOv10(You only look once v10)或DINO(DETR with improved denoising anchor boxes),获取候选目标框;第2阶段设计为“即插即用”的掩膜计算模块,无需额外训练即可基于调和函数模型对背景进行快速回归,并计算前景掩膜,从而提升掩膜计算的精度与鲁棒性。本文方法以调和函数理论及复分析中的相关定理为数学基础,以Dirichlet问题为核心框架,创新性地提出利用局部边界信息推断全局背景的实例掩膜生成策略。通过将Dirichlet问题转化为最小二乘回归形式,算法兼具可实现性与灵活性。在NWPU VHR-10数据集上的实验结果表明,与典型方法相比,本文方法在包围框平均精度(Average precision of boxes,AP-Box)和掩膜平均精度(Average precision of masks,AP-Mask)指标上均取得更优表现,其中AP-Mask指标可以在设定交并比(Intersection over union,IoU)指标为50%时达到92.1%,较现有最佳结果提升2.5个百分点。结果验证了该方法在遥感目标分割任务中的有效性与应用潜力。展开更多
This paper explores potential of Remote Sensing and Geospatial Information Systems as viable tools for data collection, processing, transformation and adjustment of cadastral data discrepancies often noted by geospati...This paper explores potential of Remote Sensing and Geospatial Information Systems as viable tools for data collection, processing, transformation and adjustment of cadastral data discrepancies often noted by geospatial practitioners during rasterization and vectorization of land related data. Necessary datasets were collected employing main approach/procedure of scanning, georeferencing, digitization, transformation and analysis in that order, to amalgamate and harmonize all datasets into one common projection and coordinate system （Universal Transverse Mercator （UTM） on Arc-Datum 1960）. Discrepancies in derived areas against recorded values in land registries were noted, smaller parcels exhibited smaller discrepancies and vice versa. Discrepancies were found to be directly proportional to the parcel areas/sizes although large parcels （〉 1000 m2） exhibited abnormally high discrepancies. This procedure yielded systematic discrepancies that could be minimized by use of a fifth order polynomial. Resultant residuals were found to be tolerably low and could be ignored for small parcels （〈 1000 m2）. Final outputs included automated GIS geodatabase cadastre, containing cadastral attributes harmonized to one projection and coordinate system that can be overlaid to other datasets from engineering design and construction works, geological and geotechnical investigation surveys, etc. tied to Remote Sensing data without the requirement of further transformations.展开更多
基金supported by the Competitive Research Fund of the University of Aizu,Japan(Grant No.P-13).
文摘Heart disease includes a multiplicity of medical conditions that affect the structure,blood vessels,and general operation of the heart.Numerous researchers have made progress in correcting and predicting early heart disease,but more remains to be accomplished.The diagnostic accuracy of many current studies is inadequate due to the attempt to predict patients with heart disease using traditional approaches.By using data fusion from several regions of the country,we intend to increase the accuracy of heart disease prediction.A statistical approach that promotes insights triggered by feature interactions to reveal the intricate pattern in the data,which cannot be adequately captured by a single feature.We processed the data using techniques including feature scaling,outlier detection and replacement,null and missing value imputation,and more to improve the data quality.Furthermore,the proposed feature engineering method uses the correlation test for numerical features and the chi-square test for categorical features to interact with the feature.To reduce the dimensionality,we subsequently used PCA with 95%variation.To identify patients with heart disease,hyperparameter-based machine learning algorithms like RF,XGBoost,Gradient Boosting,LightGBM,CatBoost,SVM,and MLP are utilized,along with ensemble models.The model’s overall prediction performance ranges from 88%to 92%.In order to attain cutting-edge results,we then used a 1D CNN model,which significantly enhanced the prediction with an accuracy score of 96.36%,precision of 96.45%,recall of 96.36%,specificity score of 99.51%and F1 score of 96.34%.The RF model produces the best results among all the classifiers in the evaluation matrix without feature interaction,with accuracy of 90.21%,precision of 90.40%,recall of 90.86%,specificity of 90.91%,and F1 score of 90.63%.Our proposed 1D CNN model is 7%superior to the one without feature engineering when compared to the suggested approach.This illustrates how interaction-focused feature analysis can produce precise and useful insights for heart disease diagnosis.
文摘针对不同磁密幅值、频率、谐波组合等复杂激励工况下磁致伸缩建模面临的精准性问题,该文利用空间注意力机制(spatial attention mechanism,SAM)对传统的卷积神经网络(convolutional neural network,CNN)进行改进,将SAM嵌套入CNN网络中,建立SAMCNN改进型网络。再结合双向长短期记忆(bidirectional long short-term memory,BiLSTM)网络,提出电工钢片SAMCNN-BiLSTM磁致伸缩模型。首先,利用灰狼优化算法(grey wolf optimization,GWO)寻优神经网络结构的参数,实现复杂工况下磁致伸缩效应的准确表征;然后,建立中低频范围单频与叠加谐波激励等复杂工况下的磁致伸缩应变数据库,开展数据预处理与特征分析;最后,对SAMCNN-BiLSTM模型开展对比验证。对比叠加3次谐波激励下的磁致伸缩应变频谱主要分量,SAMCNN-BiLSTM模型计算值最大相对误差为3.70%,其比Jiles-Atherton-Sablik(J-A-S)、二次畴转等模型能更精确地表征电工钢片的磁致伸缩效应。
文摘It aims to draw the conclusion that the ideas of treatment in Zhen Jiu Jia Yi Jing （《针灸甲乙经》, A-B Classic on Acupuncture and Moxibustion ） can be summarized as ＂regulation＂ and ＂harmonization＂ through the research of words in the Classic, such as ＂being normal＂, ＂regulation＂ and ＂harmonization＂. The lost of regulation of a normal person shows disharmony. Regulation can make the person-being-sick become harmony and back to ＂being normal＂. ＂Regulation＂ and ＂harmonization＂ right imply the quintessence of traditional Chinese medicine.
基金supported by the National Natural Science Foundation of China(Grant Nos.12172267 and 12302014).
文摘Quasi-periodic solutions with multiple base frequencies exhibit the feature of 2π-periodicity with respect to each of the hyper-time variables.However,it remains a challenge work,due to the lack of effective solution methods,to solve and track the quasi-periodic solutions with multiple base frequencies until now.In this work,a multi-steps variable-coefficient formulation is proposed,which provides a unified framework to enable either harmonic balance method or collocation method or finite difference method to solve quasi-periodic solutions with multiple base frequencies.For this purpose,a method of alternating U and S domain is also developed to efficiently evaluate the nonlinear force terms.Furthermore,a new robust phase condition is presented for all of the three methods to make them track the quasi-periodic solutions with prior unknown multiple base frequencies,while the stability of the quasi-periodic solutions is assessed by mean of Lyapunov exponents.The feasibility of the constructed methods under the above framework is verified by application to three nonlinear systems.
文摘Conventional multilevel inverters often suffer from high harmonic distortion and increased design complexity due to the need for numerous power semiconductor components,particularly at elevated voltage levels.Addressing these shortcomings,thiswork presents a robust 15-level PackedUCell(PUC)inverter topology designed for renewable energy and grid-connected applications.The proposed systemintegrates a sensor less proportional-resonant(PR)controller with an advanced carrier-based pulse width modulation scheme.This approach efficiently balances capacitor voltage,minimizes steady-state error,and strongly suppresses both zero and third-order harmonics resulting in reduced total harmonic distortion and enhanced voltage regulation.Additionally,a novel switching algorithm simplifies the design and implementation,further lowering voltage stress across switches.Extensive simulation results validate the performance under various resistive and resistive-inductive load conditions,demonstrating compliance with IEEE-519 THD standards and robust operation under dynamic changes.The proposed sensorless PR-controlled 15-PUC inverter thus offers a compelling,cost-effective solution for efficient power conversion in next-generation renewable energy systems.
文摘随着电网换相型高压直流输电(line commutated converter based high voltage direct current,LCC-HVDC)技术的广泛应用,交直流混联电网的谐波交互问题愈加复杂,建立LCC-HVDC小信号模型是分析换流器交直流谐波耦合特性的重要手段。为此,基于谐波状态空间理论(harmonic state space, HSS)建立双端12脉动LCC-HVDC小信号模型,不仅考虑了LCC谐波传递特性,还考虑了换流变压器联结方式、控制链路延时等因素的影响。采用模块化思想分别建立各子系统谐波状态空间模型,通过接口矩阵连接为整体,使得LCC的谐波状态空间建模在易于扩展的同时,提高了精确度。最后,给出交直流谐波传递的具体表达式,并通过PSCAD仿真验证模型的准确性。所建模型不仅为后续扩展或接入更为复杂的系统奠定了基础,还可应用于双端LCC系统谐波交互稳定性评估和系统参数优化设计。
文摘本文提出了一种基于调和背景建模的二阶段实例分割方法,可实现复杂遥感图像背景下目标的快速且精细的实例分割。方法包括2个阶段:第1阶段采用可灵活替换的目标检测器,如YOLOv10(You only look once v10)或DINO(DETR with improved denoising anchor boxes),获取候选目标框;第2阶段设计为“即插即用”的掩膜计算模块,无需额外训练即可基于调和函数模型对背景进行快速回归,并计算前景掩膜,从而提升掩膜计算的精度与鲁棒性。本文方法以调和函数理论及复分析中的相关定理为数学基础,以Dirichlet问题为核心框架,创新性地提出利用局部边界信息推断全局背景的实例掩膜生成策略。通过将Dirichlet问题转化为最小二乘回归形式,算法兼具可实现性与灵活性。在NWPU VHR-10数据集上的实验结果表明,与典型方法相比,本文方法在包围框平均精度(Average precision of boxes,AP-Box)和掩膜平均精度(Average precision of masks,AP-Mask)指标上均取得更优表现,其中AP-Mask指标可以在设定交并比(Intersection over union,IoU)指标为50%时达到92.1%,较现有最佳结果提升2.5个百分点。结果验证了该方法在遥感目标分割任务中的有效性与应用潜力。
文摘This paper explores potential of Remote Sensing and Geospatial Information Systems as viable tools for data collection, processing, transformation and adjustment of cadastral data discrepancies often noted by geospatial practitioners during rasterization and vectorization of land related data. Necessary datasets were collected employing main approach/procedure of scanning, georeferencing, digitization, transformation and analysis in that order, to amalgamate and harmonize all datasets into one common projection and coordinate system （Universal Transverse Mercator （UTM） on Arc-Datum 1960）. Discrepancies in derived areas against recorded values in land registries were noted, smaller parcels exhibited smaller discrepancies and vice versa. Discrepancies were found to be directly proportional to the parcel areas/sizes although large parcels （〉 1000 m2） exhibited abnormally high discrepancies. This procedure yielded systematic discrepancies that could be minimized by use of a fifth order polynomial. Resultant residuals were found to be tolerably low and could be ignored for small parcels （〈 1000 m2）. Final outputs included automated GIS geodatabase cadastre, containing cadastral attributes harmonized to one projection and coordinate system that can be overlaid to other datasets from engineering design and construction works, geological and geotechnical investigation surveys, etc. tied to Remote Sensing data without the requirement of further transformations.
