大气红外探测仪的探测器序列定位误差

大气红外探测仪AIRS的核心是一个光栅光谱仪序列,2378个红外探测器分装在17个探测器序列上,本文以实例说明了由于探测器序列在视轴方向有偏移,即空间错误定位误差给AIRS的观测值带来的影响及其光谱分布特征,以及观测值误差对后继红外晴空订正和大气廓线反演的影响.建议以后在设计同类仪器时要避免探测器序列错误定位问题,或选用干涉式分光系统.     

Study on Mechanism of Methane Column Change Influencing Atmospheric Structure and Local Heavy Rain

In order to study the relationship between atmospheric methane content and local strong convective weather,relationships among the methane content and the atmospheric structure and the local heavy precipitation are studied by using the L3 methane daily inversion product retrieved by AIRS.The results show that the distribution of total methane column content in atmosphere is strongly affected by the topography and terrain,and the methane content fluctuates in the complex topography area,which has a good inverse correlation with the precipitation.Methane has radiation and chemical activity which can affect the ground gas radiation,change the vertical distribution of atmospheric temperature,and increase the atmospheric instability.The change of methane column could be used as a precursor to the occurrence of heavy rainfall.It can provide the new view and a reference for exploring the mechanism of local heavy rain combined with multi\|source meteorological data,analysis of atmospheric power,heat,water vapor conditions.      

生物质燃烧对中国东北地区CO浓度的影响研究

利用Aqua卫星上AIRS传感器的近地表和500hPa气压层高度的CO数据,研究了中国东北地区2012年CO时空分布特征及其变化趋势,并结合MODIS火点资料以及NCEP/NCAR的风场资料,分析了当地的生物质燃烧以及周边国家和地区CO远距离输送对研究区CO浓度的影响。研究结果表明:近地表CO浓度高值出现在冬季和春季,低值出现在夏季和秋季,2011~2013年连续3a的CO浓度与火点数的相关关系均在0.52左右,显著相关。此外,CO的分布还与当地的供暖时间、人口密度和工业分布有关:CO的高值时间与中国东北地区冬季供暖时间基本一致,人口和工业集中地区的CO浓度偏高,人口稀少的内蒙古草原CO浓度值偏低;根据NECP/NCAR的风场资料,中国东北地区500hPa气压层高度全年受来自西伯利亚和蒙古国的西北风影响,东北地区,尤其是内蒙古自治区,西伯利亚和蒙古国常年有大量火点,在500hPa气压层高度的CO浓度受西伯利亚和蒙古国的影响。生物质燃烧能够反映农作物收获时间,CO浓度的时空变化规律也能在一定程度上反映我国农作物的时空分布特征,具有重要的研究意义。     

Diagnosis of heart disease using artificial immune recognition system and fuzzy weighted pre-processing

This paper presents a novel method for diagnosis of heart disease. The proposed method is based on a hybrid method that uses fuzzy weighted pre-processing and artificial immune recognition system (AIRS). Artificial immune recognition system has showed an effective performance on several problems such as machine learning benchmark problems and medical classification problems like breast cancer, diabetes, liver disorders classification. The robustness of the proposed method is examined using classification accuracy, k-fold cross-validation method and confusion matrix. The obtained classification accuracy is 96.30% and it is very promising compared to the previously reported classification techniques.     

A real time experimental setup for classification of epilepsy risk levels

The objective of this paper is to analyze the performance of singular value decomposition, expectation maximization, and Elman Neural Networks in optimization of code converter outputs in the classification of epilepsy risk levels from EEG (electroencephalogram) signals. The signal parameters such as the total number of positive and negative peaks, spikes and sharp waves, their duration etc., were extracted using morphological operators and wavelet transforms. Code converters were considered as a level one classifier. Code converters were found to have a performance index and quality value of 33.26 and 12.74, respectively, which is low. Consequently, for the EEG signals of 20 patients, the post classifiers were applied across 3 epochs of 16 channels. After having made a comparative study of different architectures, SVD was found to be the best post classifier as it marked a performance index of 89.48 and a quality value of 20.62. Elman neural network also exhibits good performance metrics than SVD in the morphological operator based feature extraction method.     

卫星红外高光谱反演大气水汽含量

利用高光谱大气红外探测仪AIRS模拟及观测数据,发展基于主成分分析技术的多层前馈神经网络反演算法,进行大气中水汽柱总量(IWV)的反演计算、模拟及实测验证。首先,基于全球晴空大气廓线训练样本SeeBorV4.0,利用快速辐射传输模式CRTM进行了辐射传输模拟计算,得到全球高光谱分辨率模拟辐亮度;其次,利用主成分分析技术对模式模拟和AIRS实测高光谱数据进行降维、去噪及去相关处理,并采用多层前向神经网络算法反演大气水汽柱总量;最后,利用数值试验、AIRS实测L1B数据及其水汽产品,对反演算法进行了验证。通过与AIRS官方大气产品的统计分析,本算法反演均方根误差为0.387 g/cm²,最大偏差为0.82 g/cm²,空间分辨率保留了AIRS像素原分辨率(比AIRS官方大气产品高3倍)。     

云参数对AIRS亮温模拟计算的影响试验

由于云污染对大气红外遥感的严重干扰,大量红外资料遭到了舍弃。为 了充分同化红外资料,提高初始场精度和改善数值预报效果,利用通用辐射传输模式(Community Radiative Transfer Model, CRTM) 模拟了大气红外探测仪(Atmospheric Infrared Sounder, AIRS)的通道亮温,并分析了云类型、云层含水量、云厚度和云顶高度等云参数对AIRS亮温的 影响。结果表明：(1)由于云层对红外辐射的截断作用,只有高于云顶的大气才会对辐射亮温产 生影响;(2)随着云层积分含水量的增加,亮温逐渐减小,但其减速放缓,直至不变;有效半径较 大的粒子对辐射的散射作用较强,相应亮温较小;(3)若云顶高度固定不变,云厚度的变化 则不会对亮温产生影响;若云底高度固定不变,云层越厚,相应的亮温越小;(4)地面通道亮温 对云顶高度的变化比较敏感,云顶以上通道的亮温不受云顶高度变化的影响。     

An improved approach to medical data sets classification: artificial immune recognition system with fuzzy resource allocation mechanism

Abstract: The artificial immune recognition system (AIRS) has been shown to be an efficient approach to tackling a variety of problems such as machine learning benchmark problems and medical classification problems. In this study, the resource allocation mechanism of AIRS was replaced with a new one based on fuzzy logic. The new system, named Fuzzy-AIRS, was used as a classifier in the classification of three well-known medical data sets, the Wisconsin breast cancer data set (WBCD), the Pima Indians diabetes data set and the ECG arrhythmia data set. The performance of the Fuzzy-AIRS algorithm was tested for classification accuracy, sensitivity and specificity values, confusion matrix, computation time and receiver operating characteristic curves. Also, the AIRS and Fuzzy-AIRS algorithms were compared with respect to the amount of resources required in the execution of the algorithm. The highest classification accuracy obtained from applying the AIRS and Fuzzy-AIRS algorithms using 10-fold cross-validation was, respectively, 98.53% and 99.00% for classification of WBCD; 79.22% and 84.42% for classification of the Pima Indians diabetes data set; and 100% and 92.86% for classification of the ECG arrhythmia data set. Hence, these results show that Fuzzy-AIRS can be used as an effective classifier for medical problems.     

Mapping leaf chlorophyll and leaf area index using inverse and forward canopy reflectance modeling and SPOT reflectance data

Reflectance data in the green, red and near-infrared wavelength region were acquired by the SPOT high resolution visible and geometric imaging instruments for an agricultural area in Denmark (56°N, 9°E) for the purpose of estimating leaf chlorophyll content (C_ab) and green leaf area index (LAI). SPOT reflectance observations were atmospherically corrected using aerosol data from MODIS and profiles of air temperature, humidity and ozone from the Atmospheric Infrared Sounder (AIRS), and used as input for the inversion of a canopy reflectance model. Computationally efficient inversion schemes were developed for the retrieval of soil and land cover-specific parameters which were used to build multiple species and site dependent formulations relating the two biophysical properties of interest to vegetation indices or single spectral band reflectances. Subsequently, the family of model generated relationships, each a function of soil background and canopy characteristics, was employed for a fast pixel-wise mapping of C_ab and LAI.The biophysical parameter retrieval scheme is completely automated and image-based and solves for the soil background reflectance signal, leaf mesophyll structure, specific dry matter content, Markov clumping characteristics, C_ab and LAI without utilizing calibration measurements.Despite the high vulnerability of near-infrared reflectances (ρ_nir) to variations in background properties, an efficient correction for background influences and a strong sensitivity of ρ_nir to LAI, caused LAI-ρ_nir relationships to be very useful and preferable over LAI-NDVI relationships for LAI prediction when LAI > 2. Reflectances in the green waveband (ρ_green) were chosen for producing maps of C_ab.The application of LAI-NDVI, LAI-ρ_nir and C_ab-ρ_green relationships provided reliable quantitative estimates of C_ab and LAI for agricultural crops characterized by contrasting architectures and leaf biochemical constituents with overall root mean square deviations between estimates and in-situ measurements of 0.74 for LAI and 5.0 μg cm^− 2 for C_ab.The results of this study illustrate the non-uniqueness of spectral reflectance relationships and the potential of physically-based inverse and forward canopy reflectance modeling techniques for a reasonably fast and accurate retrieval of key biophysical parameters at regional scales.     

基于记忆细胞剪切和非线性资源分配的人工免疫识别系统

为减少人工免疫识别系统(AIRS)的记忆细胞数量并提高AIRS的分类准确率,提出一种基于记忆细胞剪切和非线性资源分配的人工免疫识别系统(PNAIRS).PNAIRS采用样本属性离散化来压缩训练空间,利用记忆细胞剪切来淘汰低适应度细胞,并使用非线性资源分配来优化分类器.PNAIRS对6个UCI数据集进行分类测试,测试结果与其它分类算法结果对比,显示PNAIRS具有较小规模的记忆细胞群体和较高的分类准确率,而且算法运行速度快.这表明PNAIRS算法是一个性能良好的分类算法,具有潜在的应用价值.