In this paper, we attempt to resolve the problem of grading of brain tumors as grade 2, grade 3, grade 4, using information from magnetic resonance spectroscopy (MRS) image, to assist in clinical diagnosis. This paper...In this paper, we attempt to resolve the problem of grading of brain tumors as grade 2, grade 3, grade 4, using information from magnetic resonance spectroscopy (MRS) image, to assist in clinical diagnosis. This paper proposes a novel approach to extract metabolite values represented in a graphical form in MR Spectroscopy image. Metabolites like N-acetyl aspartate (NAA), Choline (CHO) along with the metabolite ratios NAA/CHO and presence/absence of LACTATE peak play the most important role in deciding the tumor type. The proposed approach consists of several steps including preprocessing, metabolite peak height scanning and classification. Proposed system stores the metabolite values in dataset instead of storing MRS images;so reduces the image processing tasks and memory requirements. Further these metabolite values and ratios are fed to a BPN classifier. Experimental results demonstrate the effectiveness of the proposed approach in classifying the brain tumors.展开更多
【目的】叶绿素含量可以用来评价棉花的长势情况,快速、准确和大面积监测棉花叶绿素含量,有助于实现精准农业。【方法】分别用0~2阶(步长为0.2)的分数阶微分处理和1~10尺度下的小波变换对田间测定的陆地棉和海岛棉等2种棉花的高光谱反...【目的】叶绿素含量可以用来评价棉花的长势情况,快速、准确和大面积监测棉花叶绿素含量,有助于实现精准农业。【方法】分别用0~2阶(步长为0.2)的分数阶微分处理和1~10尺度下的小波变换对田间测定的陆地棉和海岛棉等2种棉花的高光谱反射率进行处理,提高棉花叶绿素含量反演精度。通过分析不同处理方式的光谱与叶绿素含量之间的相关性,筛选得出敏感波段;并运用支持向量机回归和随机森林回归模型分别构建棉花叶绿素含量高光谱估算模型。【结果】(1)在全波段范围内,2种棉花325~1075 nm光谱反射率曲线整体变化趋势基本相同,其反射率均随着叶绿素含量的增加而增大。(2)经连续小波变换和分数阶微分变换后,2种棉花高光谱数据和叶绿素含量的相关性有所增强。使用随机森林回归和小波能量系数7对陆地棉叶绿素含量的反演效果最好,建模集决定系数(coefficient of determination,R^(2))为0.931,均方根误差(root mean square error,RMSE)为0.782,剩余预测偏差(residual prediction deviation,RPD)为2.162;使用随机森林回归和小波能量系数6对海岛棉叶绿素含量的反演效果最佳,建模集R^(2)为0.932,RMSE为1.198,RPD为2.687。【结论】本研究可为棉花叶绿素含量遥感估算提供技术参考。展开更多
When exploring the temporal and spatial change law of ocean environment, the most common method used is using smaller-scale observed data to derive the change law for a larger-scale system. For instance, using 30-year...When exploring the temporal and spatial change law of ocean environment, the most common method used is using smaller-scale observed data to derive the change law for a larger-scale system. For instance, using 30-year observation data to derive 100-year return period design wave height. Therefore, the study of inherent self-similarity in ocean hydrological elements becomes increasingly important to the study of multi-year return period design wave height derivation. In this paper, we introduced multifractal to analyze the statistical characteristics of wave height series data observed from oceanic hydrological station. An improvement is made to address the existing problems of the multifractal detrended fluctuation analysis (MF-DFA) method, where trend function showed a discontinuity between intervals. The improved MFDFA method is based on signal mode decomposition, replacing piecewise polynomial fitting used in the original method. We applied the proposed method to the wave height data collected at Chaolian Island, Shandong, China, from 1963 to 1989 and was able to conclude the wave height sequence presented weak multi-fractality. This result provided strong support to the past research on the derivation of multi-year return period design wave height with observed data. Moreover, the new method proposed in this paper also provides a new perspective to explore the intrinsic characteristic of data.展开更多
应用瑞典Raminstorp研究区Bio SAR 2007 P-波段多基线In SAR数据,研究了基于多基线干涉SAR数据的层析方法,成功提取了可代表森林垂直结构信息的雷达后向散射功率垂直分布信息,并基于该信息提取了树高。应用地面实测样地对树高提取精度...应用瑞典Raminstorp研究区Bio SAR 2007 P-波段多基线In SAR数据,研究了基于多基线干涉SAR数据的层析方法,成功提取了可代表森林垂直结构信息的雷达后向散射功率垂直分布信息,并基于该信息提取了树高。应用地面实测样地对树高提取精度进行了检验,结果表明:HH极化树高提取精度最高(R2为0.65,RMSE为2.35 m,相关系数为0.80),HV其次,VV最差。展开更多
文摘In this paper, we attempt to resolve the problem of grading of brain tumors as grade 2, grade 3, grade 4, using information from magnetic resonance spectroscopy (MRS) image, to assist in clinical diagnosis. This paper proposes a novel approach to extract metabolite values represented in a graphical form in MR Spectroscopy image. Metabolites like N-acetyl aspartate (NAA), Choline (CHO) along with the metabolite ratios NAA/CHO and presence/absence of LACTATE peak play the most important role in deciding the tumor type. The proposed approach consists of several steps including preprocessing, metabolite peak height scanning and classification. Proposed system stores the metabolite values in dataset instead of storing MRS images;so reduces the image processing tasks and memory requirements. Further these metabolite values and ratios are fed to a BPN classifier. Experimental results demonstrate the effectiveness of the proposed approach in classifying the brain tumors.
文摘【目的】叶绿素含量可以用来评价棉花的长势情况,快速、准确和大面积监测棉花叶绿素含量,有助于实现精准农业。【方法】分别用0~2阶(步长为0.2)的分数阶微分处理和1~10尺度下的小波变换对田间测定的陆地棉和海岛棉等2种棉花的高光谱反射率进行处理,提高棉花叶绿素含量反演精度。通过分析不同处理方式的光谱与叶绿素含量之间的相关性,筛选得出敏感波段;并运用支持向量机回归和随机森林回归模型分别构建棉花叶绿素含量高光谱估算模型。【结果】(1)在全波段范围内,2种棉花325~1075 nm光谱反射率曲线整体变化趋势基本相同,其反射率均随着叶绿素含量的增加而增大。(2)经连续小波变换和分数阶微分变换后,2种棉花高光谱数据和叶绿素含量的相关性有所增强。使用随机森林回归和小波能量系数7对陆地棉叶绿素含量的反演效果最好,建模集决定系数(coefficient of determination,R^(2))为0.931,均方根误差(root mean square error,RMSE)为0.782,剩余预测偏差(residual prediction deviation,RPD)为2.162;使用随机森林回归和小波能量系数6对海岛棉叶绿素含量的反演效果最佳,建模集R^(2)为0.932,RMSE为1.198,RPD为2.687。【结论】本研究可为棉花叶绿素含量遥感估算提供技术参考。
基金Supported by the NSFC-Shandong Joint Fund “Study on the DisasterCausing Mechanism and Disaster Prevention Countermeasures of MultiSource Storm Surges”(No.U1706226)the National Natural Science Foundation of China “Coastal Engineering and Risk Assessment Based on a Four-Layer Nested Multi-Objective Probability Model”(No.51379195)+1 种基金the Natural Science Foundation of Shandong Province “Three-Layer Nested Multi-Objective Probability Prediction and Risk Assessment in Coastal Engineering”(No.ZR2013EEM034)the Program of Promotion Plan for Postgraduates’ Educational Quality “Paying More Attention to the Study on the Cultivation Mode of Mathematical Modeling for Engineering Postgraduates”(No.861801232417)
文摘When exploring the temporal and spatial change law of ocean environment, the most common method used is using smaller-scale observed data to derive the change law for a larger-scale system. For instance, using 30-year observation data to derive 100-year return period design wave height. Therefore, the study of inherent self-similarity in ocean hydrological elements becomes increasingly important to the study of multi-year return period design wave height derivation. In this paper, we introduced multifractal to analyze the statistical characteristics of wave height series data observed from oceanic hydrological station. An improvement is made to address the existing problems of the multifractal detrended fluctuation analysis (MF-DFA) method, where trend function showed a discontinuity between intervals. The improved MFDFA method is based on signal mode decomposition, replacing piecewise polynomial fitting used in the original method. We applied the proposed method to the wave height data collected at Chaolian Island, Shandong, China, from 1963 to 1989 and was able to conclude the wave height sequence presented weak multi-fractality. This result provided strong support to the past research on the derivation of multi-year return period design wave height with observed data. Moreover, the new method proposed in this paper also provides a new perspective to explore the intrinsic characteristic of data.
