共查询到20条相似文献，搜索用时 31 毫秒
1.
Correlation, multiple regression, and path analyses were used to investigate the relationships between body weight and three other morphological traits in juvenile Japanese sea cucumbers Apostichopus japonicus. We measured live body weight(BW), body length(BL), numbers of papillae(NP), and numbers of tube feet(NF) at 60, 80, 100, and 130 days post-hatching(dph). We calculated path correlation coe cients, correlation indices( R~2), and coe cients of determination with BW as the dependent variable and the other morphological traits as independent variables. The coe cient of variation for BW was high across all age groups, and all measured morphological traits were significantly correlated( P 0.01). BL had the greatest direct ef fect on BW across all age groups(60 dph, 0.526; 80 dph, 0.404; 100 dph, 0.620;and 130 dph, 0.681), while NF had the greatest indirect ef fect on BW across all age groups(60 dph, 0.528;80 dph, 0.452; 100 dph, 0.666; and 130 dph, 0.603). Regression analyses between morphological traits and BW indicated that R 2 was greater than 0.85 only in the 100-dph specimens. The indirect ef fects of the other measured morphological traits on BW were age-dependent. The optimal regression equations,as determined with stepwise regression, were, for 60-dph specimens: BW_(60)=10~((-3.04+0.092 BL+0.014 NP+0.014 NF))( R~2 =0.632); for 80-dph specimens: BW _(80)=10~((-3.035+0.056 BL+0.017 NP+0.02 NF))( R~2 =0.686); for 100-dph specimens:BW_(100) =10~((-3.742+0.069 BL+0. 633*l g( NP)+0. 464*l g( NF)))( R~2 =0.893); and for 130-dph specimens: BW_(130)=10~((-2.472+0.065 BL+0.012 NP))( R~2 =0.774). Our work clarified the correlation between various morphological traits and body weight of a commercially-important sea cucumber species( A. japonicus). Our predictive models for body weight might be useful for the aquaculture and selective breeding of A. japonicus. These models might also provide theoretical support for the indirect selection of traits that are di cult to select directly. 相似文献
2.
建立大坝变形预测的支持向量机模型,并用遗传算法对支持向量机模型的核函数参数、惩罚参数和损失参数进行优化。将同一优化方法不同支持向量机核函数、不同优化方法同种支持向量机核函数进行横向对比,将BP神经网络、自回归AR(p)模型、多元回归分析法和周期函数拟合法进行纵向对比。结果表明,该GA-SVM(RBF)模型不仅能较好地预测大坝的变形趋势,而且能大幅提高预测精度。 相似文献
3.
矿区地裂缝精准识别对防灾、减灾和生态环境修复具有重要意义。针对高分辨率无人机影像较难自动精确提取地裂缝的问题,本文提出了一种基于改进主动轮廓模型的无人机影像矿区地裂缝提取方法。首先,采用Otsu算法计算背景和地裂缝初值作为先验知识;其次,构建背景和地裂缝初值的提取能量函数,并引入到传统CV主动轮廓模型,增强地裂缝提取的针对性;最后,通过轮廓的不断演化实现地裂缝的提取。以内蒙古扎赉诺尔矿区为研究区、无人机影像为数据源,采用改进主动轮廓模型方法进行地裂缝提取,并与传统的Canny边缘检测算法、支持向量机（SVM）、最大似然（MLM）和传统CV主动轮廓模型方法进行对比分析。结果表明：在地物类型较为单一的小范围区域,传统的Canny边缘检测算法和传统CV主动轮廓模型提取效果较差,改进主动轮廓模型、SVM和MLM共3种方法均可以取得较好的效果,其中,改进主动轮廓模型方法精度最高;在地物类型相对复杂的大范围区域,传统的Canny边缘检测算法、SVM、MLM和传统CV主动轮廓模型方法存在较多的漏提和误提,Kappa系数均低于0.7,而本文改进主动轮廓方法依然可以取得较好的效果,Kappa系数达到0.9左右。因此,本文提出的方法通过引入先验知识可有效提高地裂缝提取的精度和稳定性。 相似文献
4.
一种基于熵权法的小波去噪复合评价指标 总被引：2，自引：0，他引：2
传统的评价指标在真值未知的情况下不能满足小波去噪质量评价的要求。为此，借助变化率特征重新构建均方根误差变化量和平滑度变化量两个指标，利用熵权法定权将归一化后的两个指标线性组合，所得到的新指标即为复合评价指标。该方法借助指标的变化率随分解层数的增加表现出明显的收敛特性来确定去噪最优分解层数。实验表明，该方法能够在真值未知的情况下准确地指导小波分解，确定去噪最优分解层数，从而达到最优去噪效果。 相似文献
5.
介绍一种稀疏的贝叶斯学习算法——关联向量机(RVM)，它在再生核希尔伯特空间中学习，利用贝叶斯方法推理，推广能力好，与支持向量机相比不仅解更为稀疏而且不需要调整超参数。应用RVM的对小样本的良好分类能力，提出一种基于RVM的入侵检测原型系统。 相似文献
6.
基于支持向量机理论的地下水动态遥感监测模型与应用 总被引：2，自引：0，他引：2
地下水是我国内陆干旱地区水资源的重要组成部分,也是极为敏感的生态环境因素之一。地下水动态变化影响着绿洲和湿地的演化,以及土地资源的开发。西北地区地下水监测网尚不完善,动态资料相对缺乏。遥感技术可以弥补传统地下水位监测手段的不足。由于降水极少,西北干旱区地表反射率与地下水水位埋深关系极其密切。选用归一化植被指数(NDVI)、地表温度(LST)数据,应用支持向量机回归方法,建立西北干旱地区地下水位遥感监测模型。提取MODIS影像中的NDVI和LST产品上的地表温度和植被指数信息,作为模型的输入,通过合理选择核函数进行支持向量机的回归分析,从而建立地表植被指数、地表温度与地下水位的相关数学模型,并分析了不同核函数所拟合结果。在河西走廊疏勒河流域的研究成果表明,运用MODIS数据开发地下水动态模型反演水位变化是可行的,模型拟合的结果比较符合实际情况,尤其是对于细土平原地下水浅埋地区模型应用效果更为理想。一次多项式核函数适合模拟埋深小于3m浅埋地下水,径向基函数RBF核函数和三次多项式核函数法则更适合模拟较大埋深情况。开发的地下水位遥感监测模型可为西北干旱区水循环研究和流域水资源管理提供技术手段。 相似文献
7.
特高压工程施工利用高分二号遥感影像进行水土保持远程监测研究 总被引：2，自引：0，他引：2
论述了遥感影像中图像正射校正、图像融合和支持向量机等遥感技术在国产高分二号影像中的应用,并展示了其研究成果应用于特高压工程水土保持远程监测效果。在实施中,对特高压工程施工期和试运行期分别进行监测,首先利用图像正射校正、影像融合以及支持向量机分类等遥感技术获取特高压工程水土保持远程监测各个要素面积,即施工期扰动土地总面积,试运行期扰动土地的整治面积、可恢复林草植被面积和林草类植被面积,进而计算水土保持效果评价的3个评价指标,即扰动土地整治率、林草植被恢复率和林草覆盖率。将研究成果应用于锡盟-山东特高压交流输变电施工过程中,实验结果表明,高分二号遥感影像技术能够有效应用于特高压工程水土保持远程监测,为特高压工程水保监督提供了优质低价、可长期持续的一种远程监测方法。 相似文献
8.
《中国海洋大学学报(英文版)》2016,(4)
In this study, molecular weight controllable degradation of algal Laminaria japonica polysaccharides(LPS) was investigated by ultrasound combined with hydrogen peroxide. Three main factors, i.e., ultrasonic power(A), ultrasonic time(B), and H_2O_2 concentration(C) were chosen for optimizing parameters by employing three-factors, three-levels BBD. The influence of degradation on structure change and antioxidant activities was also investigated. A second-order polynomial equation including molecular weight(Y) of Laminaria japonica polysaccharides and each variable parameter, i.e., ultrasonic power(A), ultrasonic time(B), and H_2O_2 concentration(C), was established: Y=20718.67-4273.13A-4000.38B-1438.75C+2333.25AB+1511.00AC+873.00BC+2838.29A~2 + 2490.79B~2+873.04C~2. The equation regression coefficient value(R~2 = 0.969) indicated that this equation was valid. The value of the adjusted determination coefficient(adjusted R~2 = 0.914) also confirmed that the model was highly significant. The results of selected experimental degradation conditions matched with the predicted value. FT-IR spectra revealed that the structures of LPS before and after degradation were not significantly changed. Antioxidant activities of LPS revealed that low Mws possessed stronger inhibitory than the original polysaccharides. The scavenging effects on superoxide radicals was the highest when IC50 of crude LPS was 4.92 mg mL~(-1) and IC50 of Mw 18.576 KDa was 1.02 mg mL~(-1), which was fourfold higher than initial polysaccharide. 相似文献
9.
以三峡库区秭归-巴东段为例,将地理加权回归(GWR)模型引入到研究区的空间尺度分割方法中,利用粒子群优化(PSO)算法对支持向量机(SVM)模型参数进行优化,构建GWR-PSO-SVM耦合模型,完成研究区滑坡易发性评价,并与传统的PSO-SVM耦合模型结果进行对比。结果表明,在特定类别精度分析、总体预测精度分析和曲线下面积分析中,本文方法评价效果均优于传统方法。 相似文献
10.
运动目标检测是计算机视觉监视系统的核心。对于采用固定摄像机监控视频运动目标的检测,利用Affine Lucas Kanade特征跟踪算法的图像金字塔模型,根据模型的不同层数,将对应不同层数分辨率下的差分图像与Susan算子结合,通过形态学处理实现对复杂背景下运动目标的检测。仿真实验结果表明,采用的算法有效地抑制了噪声对运动目标检测效果的影响,且计算量随金字塔层数的增加而成倍减少。 相似文献
11.
LIU Guiying WANG Xuda GE Kun WU Jinhao WANG Zhaohui DU Jing SONG Lun ZHOU Zunchun 《中国海洋大学学报(英文版)》2022,21(2):473-478
Apostichopus japonicus is an important invertebrate that is widely used as a tonic food in Asian countries.The purpose of this study is to purify and identify a class of compound,the saponins,from the body wall of A.japonicus,and to establish a new me-thod to determine the quantity of saponins in the sea cucumber.In this study,the saponins of A.japonicus,cladoloside A(CA),were ob-tained from 80%ethanol extract by column chromatography for the first time and were characterized using the spectral method.The resulting purified saponins were then profiled using 1HNMR,13CNMR,and ESI-MS,which revealed the CA molecular formula of C53H82O2 and contained a triterpenoid backbone,a methylglucopyranosyl moiety,a quinovopyranosyl,and two xylopyranosyls.A me-thod for the quantitative determination of CA,comprising microwave-assisted extraction,high-performance liquid chromatography,and diode array detector method,was established.Extraction efficiency was optimized by changing microwave power,extraction sol-vent,volume,time,and temperature.Results showed that under the optimum conditions(extraction time of 10 min,temperature of 45℃,and solvent of 25 mL 70%ethanol under 400 W),the detection limit of CA was 0.0015 mg mL?1,and the recoveries of CA from samples at spiking levels of 10,20,and 50μg g?1 ranged from 90.1%-104%.The proposed method was successfully applied to ana-lyze the saponins in different tissues of A.japonicus collected in different seasons.The method developed in this study can provide quantitative technical support for the quality control of A.japonicus. 相似文献
12.
基于确定性系数和支持向量机的地质灾害易发性评价 总被引：2，自引：0，他引：2
确定性系数（Certainty Factor,CF）是经典的地质灾害影响因子敏感性分析方法;支持向量机（Support Vector Machine, SVM）作为机器学习的代表方法,能够综合各个影响因子的关系,对地质灾害易发性进行评价。本文以云南省怒江州泸水县为研究区,将高程、坡度、坡向、剖面曲率、距断裂的距离、距河网的距离、距路网的距离、地貌类型、岩土体类型、土地利用类型作为该区域地质灾害影响因子,依据各影响因子灾害面积比和分级面积比曲线对影响因子的状态进行分级。根据381个地质灾害隐患点,采用CF方法计算的各个影响因子的敏感性值,作为SVM的分类数据,建立基于CF-SVM的易发性评估模型,同时与单独SVM模型的评价结果进行对比分析。结果表明,CF-SVM模型得到的极高和高易发区主要分布在怒江两岸河谷地带,涵盖了89.76%的地质灾害隐患点,比单独SVM模型具有更高的成功率;利用ROC曲线和P-R曲线对两个模型进行检验,CF-SVM模型的评价精度分别达到92%和88%,均高于单独的SVM。由此说明,CF-SVM模型对地质灾害易发性评价有较高的预测价值,可以为地质灾害风险评估和管理提供依据。 相似文献
13.
��������Ⱥ֧�������������ǵ��θ�����GPS�߳���� 总被引：1，自引：0，他引：1
?о?????????????????????GPS???????е?????????????????????????????????θ??????????μ??????????????????????????????????????????????????????????????????????SVM??????????????????????????????淨?????溯??????BP?????編???????????侫?????? 相似文献
14.
基于支持向量机的岩石薄片图像分割 总被引：4，自引：0，他引：4
支持向量机是对传统学习分类方法的一个良好替代,特别是小样本、高维的情况下,有着良好的泛化能力,利用支持向量机良好的分类特性,将图像分割的问题转化为分类问题,对岩石薄片图像进行分割实验.通过实验表明：支持向量机对于分割颜色分布不均匀、边缘模糊的岩石薄片图像,有很好的应用前景. 相似文献
15.
Newmark位移模型是研究地震滑坡易发性的经典模型,机器学习方法支持向量机模型也越来越多的应用到滑坡易发性评估研究。本文将Newmark位移模型与支持向量机模型相结合,建立基于物理机理的地震滑坡易发性评估模型并应用于2008年汶川地震重灾区汶川县。从震后遥感影像目视解译出汶川县1900处地震诱发滑坡,并将其随机划分为70%的训练数据集和30%的验证数据集。选择地形起伏度、坡度、地形曲率、与构造断裂带距离、与水系距离、与道路距离6个因子与Newmark位移值共同作为地震滑坡易发性影响因素。利用ROC曲线和模型不确定性等指标对模型结果进行评估,并与二元统计模型频率比和多元统计模型Logistic回归的结果进行对比。结果表明：与频率比和Logistic回归模型相比,支持向量机模型的正确率最高,训练集和验证集ROC曲线下的面积分别为0.876和0.851。将模型应用于绘制汶川县地震滑坡易发性图,结果显示滑坡易发性图与实际的滑坡点位分布一致性较高,有80.4%的滑坡位于极高和高易发区。这说明支持向量机与Newmark位移方法结合建立的地震滑坡易发性评估模型有较高的预测价值,可以为滑坡风险评估和管理提供依据。 相似文献
16.
1 Introduction TheROV (RemoteOperatedVehicle)isakindofsystemthatcanbeusedforunderwatermeasurementanddetection (Caimi,1996 ;KevernandLeGall,1991) .Inthispaper ,theirradianceofthelightre flectedbythetargetthroughwaterbodiesindifferentconditionsissimulatedbyacomputer .Underdiffer entwaterconditions,therelationbetweentheirradi anceandthedistanceispresented .Thenthemaxi mumdetectiondistanceofthedetectorcanbeob tained .WealsorestoretheunderwaterblurryimagesusingtheWienerfilterbasedonthesimula… 相似文献
17.
混合像元是遥感影像中普遍存在的现象,对此,本文提出基于加权后验概率的支持向量机进行影像混合像元分解。该分类算法可判定端元种类的同时得到每种地物的后验概率,从而进行非线性模型的混合像元分解。由于加权后验概率的支持向量机分类算法能够减少分类器受土地覆盖类型模糊样本点的干扰,因此,改善了非线性混合像元分解模型的精度。首先,由样本点计算得到核函数参数值,然后,计算影像中每一种土地覆盖类型的后验概率,将其作为各个两类支持向量机分类器的权系数并求得多类后验概率值,确定影像每一种土地覆盖类型并得到丰度值。本文采用TM多波段遥感影像验证该方法的可行性,实验区位于我国东北部的大兴安岭中北段地区,土地覆盖类型包含农田、居民地、水体、荒地等。将本文提出的混合像元分解方法结果与标准支持向量机模型分解的结果对比表明,以加权后验概率的支持向量机遥感影像混合像元分解方法精度优于标准支持向量机模型。 相似文献
18.
不同机器学习预测滑坡易发性的建模过程及其不确定性有所差异, 另外如何有效识别滑坡易发性的主控因子意义重大。针对上述问题, 以支持向量机(support vector machine, 简称SVM)和随机森林(random forest, 简称RF)为例探讨了基于机器学习的滑坡易发性预测及其不确定性, 创新地提出了"权重均值法"来综合计算出更准确的滑坡主控因子。首先获取陕西省延长县滑坡编录和10类基础环境因子, 将因子频率比值作为SVM和RF的输入变量; 再将滑坡与随机选择的非滑坡样本划分为训练集和测试集, 用训练好的机器学习预测出滑坡易发性并制图; 最后用受试者工作曲线、均值和标准差等来评估建模不确定性, 并计算滑坡主控因子。结果表明: ①机器学习能有效预测出区域滑坡易发性, RF预测的滑坡易发性精度高于SVM, 而其不确定性低于SVM, 但两者的易发性分布规律整体相似; ②权重均值法计算出延长县滑坡主控因子依次是坡度、高程和岩性。实例分析和文献综述显示RF模型相较于其他机器学习模型属于可靠性较高的易发性模型。 相似文献
19.
The exceptionally large individual growth variation has been previously recognized in several sea cucumber cohorts. However, there is a lack of information regarding the mechanism of such individual differences. In this study, the sea cucumber Apostichopus japonicus(Selenka)was reared individually in order to eliminate possible effects of social interaction, stocking density, etc. The results showed that there were substantial differences in growth among the sea cucumber individuals during the 100-day experiment. The special growth rate of the sea cucumber individuals differed by up to three folds(from 0. 40% to 1.01%), and the coefficient of variation in body weight increased from 12. 04% to 40. 51%. The final wet body weight, food intake and food conversion efficiency for each sea cucumber were generally positively correlated with their initial wet body weight(P<0. 05). Energy budget of the animals showed that the food energy spent on respiration was much greater(about four folds)but energy deposited for growth was much less for(initially)smaller than for larger A. Japonicus. The present result implies that there are obvious genetic differences among the sea cucumber individuals, largely accounting for the individual growth variation of the cohort sea cucumber. These results will provide some basic data for promoting selective breeding and farming of the sea cucumber. 相似文献
20.
The relationship between microsatellite polymorphism and body weight of captive bred Chinese sea cucumber Apostichopus japonicus was investigated in two local populations in Dalian.Among ten loci discovered, nine show changes except for A J07 loci. Seven loci were found highly polymorphic in both populations. For each locus in two populations, the average number of alleles is 6.428 6 and 6.285 7, the average observed heterozygosity at 0.225 7 and 0.245 9, the expected heterozygosity at 0.776 8 and 0.748 8, the polymorphism information content (PIC) at 0.709 2 and 0.674 6, respectively. Further analysis show significant correlation between A. japonicus body weight and occurrence markers AJ02 and AJ04. The findings of the relation may be helpful for molecular breeding,as well as the marker-assisted selection of sea cucumbers. 相似文献