期刊文献+
共找到990篇文章
< 1 2 50 >
每页显示 20 50 100
A Spectral Convolutional Neural Network Model Based on Adaptive Fick’s Law for Hyperspectral Image Classification
1
作者 Tsu-Yang Wu Haonan Li +1 位作者 Saru Kumari Chien-Ming Chen 《Computers, Materials & Continua》 SCIE EI 2024年第4期19-46,共28页
Hyperspectral image classification stands as a pivotal task within the field of remote sensing,yet achieving highprecision classification remains a significant challenge.In response to this challenge,a Spectral Convol... Hyperspectral image classification stands as a pivotal task within the field of remote sensing,yet achieving highprecision classification remains a significant challenge.In response to this challenge,a Spectral Convolutional Neural Network model based on Adaptive Fick’s Law Algorithm(AFLA-SCNN)is proposed.The Adaptive Fick’s Law Algorithm(AFLA)constitutes a novel metaheuristic algorithm introduced herein,encompassing three new strategies:Adaptive weight factor,Gaussian mutation,and probability update policy.With adaptive weight factor,the algorithmcan adjust theweights according to the change in the number of iterations to improve the performance of the algorithm.Gaussianmutation helps the algorithm avoid falling into local optimal solutions and improves the searchability of the algorithm.The probability update strategy helps to improve the exploitability and adaptability of the algorithm.Within the AFLA-SCNN model,AFLA is employed to optimize two hyperparameters in the SCNN model,namely,“numEpochs”and“miniBatchSize”,to attain their optimal values.AFLA’s performance is initially validated across 28 functions in 10D,30D,and 50D for CEC2013 and 29 functions in 10D,30D,and 50D for CEC2017.Experimental results indicate AFLA’s marked performance superiority over nine other prominent optimization algorithms.Subsequently,the AFLA-SCNN model was compared with the Spectral Convolutional Neural Network model based on Fick’s Law Algorithm(FLA-SCNN),Spectral Convolutional Neural Network model based on Harris Hawks Optimization(HHO-SCNN),Spectral Convolutional Neural Network model based onDifferential Evolution(DE-SCNN),SpectralConvolutionalNeuralNetwork(SCNN)model,and SupportVector Machines(SVM)model using the Indian Pines dataset and PaviaUniversity dataset.The experimental results show that the AFLA-SCNN model outperforms other models in terms of Accuracy,Precision,Recall,and F1-score on Indian Pines and Pavia University.Among them,the Accuracy of the AFLA-SCNN model on Indian Pines reached 99.875%,and the Accuracy on PaviaUniversity reached 98.022%.In conclusion,our proposed AFLA-SCNN model is deemed to significantly enhance the precision of hyperspectral image classification. 展开更多
关键词 Adaptive Fick’s law algorithm spectral convolutional neural network metaheuristic algorithm intelligent optimization algorithm hyperspectral image classification
下载PDF
Spectral matching algorithm based on nonsubsampled contourlet transform and scale-invariant feature transform 被引量:4
2
作者 Dong Liang Pu Yan +2 位作者 Ming Zhu Yizheng Fan Kui Wang 《Journal of Systems Engineering and Electronics》 SCIE EI CSCD 2012年第3期453-459,共7页
A new spectral matching algorithm is proposed by us- ing nonsubsampled contourlet transform and scale-invariant fea- ture transform. The nonsubsampled contourlet transform is used to decompose an image into a low freq... A new spectral matching algorithm is proposed by us- ing nonsubsampled contourlet transform and scale-invariant fea- ture transform. The nonsubsampled contourlet transform is used to decompose an image into a low frequency image and several high frequency images, and the scale-invariant feature transform is employed to extract feature points from the low frequency im- age. A proximity matrix is constructed for the feature points of two related images. By singular value decomposition of the proximity matrix, a matching matrix (or matching result) reflecting the match- ing degree among feature points is obtained. Experimental results indicate that the proposed algorithm can reduce time complexity and possess a higher accuracy. 展开更多
关键词 point pattern matching nonsubsampled contourlet transform scale-invariant feature transform spectral algorithm.
下载PDF
Improved Spectral Clustering Clothing Image Segmentation Algorithm Based on Sparrow Search Algorithm 被引量:1
3
作者 HUANG Wenan QIAN Suqin 《Journal of Donghua University(English Edition)》 CAS 2022年第4期340-344,共5页
In the process of clothing image researching,how to segment the clothing quickly and accurately and retain the clothing style details as much as possible is the basis of subsequent image analysis.Spectral clustering c... In the process of clothing image researching,how to segment the clothing quickly and accurately and retain the clothing style details as much as possible is the basis of subsequent image analysis.Spectral clustering clothing image segmentation algorithm is a common method in the process of clothing image extraction.However,the traditional model requires high computing power and is easily affected by the initial center of clustering.It often falls into local optimization.Aiming at the above two points,an improved spectral clustering clothing image segmentation algorithm is proposed in this paper.The Nystrom approximation strategy is introduced into the spectral mapping process to reduce the computational complexity.In the clustering stage,this algorithm uses the global optimization advantage of the particle swarm optimization algorithm and selects the sparrow search algorithm to search the optimal initial clustering point,to effectively avoid the occurrence of local optimization.In the end,the effectiveness of this algorithm is verified on clothing images in each environment. 展开更多
关键词 clothing segmentation spectral clustering particle swarm optimization algorithm intelligent fashion design
下载PDF
The measuring of spectral emissivity of object using chaotic optimal algorithm
4
作者 杨春玲 王宇野 +1 位作者 赵东阳 赵国良 《Chinese Physics B》 SCIE EI CAS CSCD 2005年第10期2041-2045,共5页
There exist a considerable variety of factors affecting the spectral emissivity of an object. The authors have designed an improved combined neural network emissivity model, which can identify the continuous spectral ... There exist a considerable variety of factors affecting the spectral emissivity of an object. The authors have designed an improved combined neural network emissivity model, which can identify the continuous spectral emissivity and true temperature of any object only based on the measured brightness temperature data. In order to improve the accuracy of approximate calculations, the local minimum problem in the algorithm must be solved. Therefore, the authors design an optimal algorithm, i.e. a hybrid chaotic optimal algorithm, in which the chaos is used to roughly seek for the parameters involved in the model, and then a second seek for them is performed using the steepest descent. The modelling of emissivity settles the problems in assumptive models in multi-spectral theory. 展开更多
关键词 spectral emissivity radiation thermometric chaotic optimal algorithm
原文传递
A SPECTRAL ESTIMATION ALGORITHM USING THE HOUSEHOLDER TRANSFORM
5
作者 余辉里 《Journal of Electronics(China)》 1991年第1期77-85,共9页
Householder transform is used to triangularize the data matrix, which is basedon the near prediction error equation. It is proved that the sum of squared residuals for eachAR order can be obtained by the main diagonal... Householder transform is used to triangularize the data matrix, which is basedon the near prediction error equation. It is proved that the sum of squared residuals for eachAR order can be obtained by the main diagonal elements of upper triangular matrix, so thecolumn by column procedure can be used to develop a recursive algorithm for AR modeling andspectral estimation. In most cases, the present algorithm yields the same results as the covariancemethod or modified covariance method does. But in some special cases where the numerical ill-conditioned problems are so serious that the covariance method and modified covariance methodfail to estimate AR spectrum, the presented algorithm still tends to keep good performance. Thetypical computational results are presented finally. 展开更多
关键词 AR spectral estimation Householder TRANSFORM AR PARAMETER RECURSIVE algorithm
下载PDF
Fast identification of mural pigments at Mogao Grottoes using a LIBS-based spectral matching algorithm
6
作者 Yiming ZHANG Duixiong SUN +4 位作者 Yaopeng YIN Zongren YU Bomin SU Chenzhong DONG Maogen SU 《Plasma Science and Technology》 SCIE EI CAS CSCD 2022年第8期23-31,共9页
To quickly identify the mineral pigments in the Dunhuang murals,a spectral matching algorithm(SMA)based on four methods was combined with laser-induced breakdown spectroscopy(LIBS)for the first time.The optimal range ... To quickly identify the mineral pigments in the Dunhuang murals,a spectral matching algorithm(SMA)based on four methods was combined with laser-induced breakdown spectroscopy(LIBS)for the first time.The optimal range of LIBS spectrum for mineral pigments was determined using the similarity value between two different types of samples of the same pigment.A mineral pigment LIBS database was established by comparing the spectral similarities of tablets and simulated samples,and this database was successfully used to identify unknown pigments on tablet,simulated,and real mural debris samples.The results show that the SMA method coupled with the LIBS technique has great potential for identifying mineral pigments. 展开更多
关键词 mural pigments laser-induced breakdown spectroscopy fast identification and classification spectral matching algorithm spectral database
下载PDF
A blind modulation recognition algorithm based on cyclic spectral correlation
7
作者 高玉龙 Zhang Zhongzhao 《High Technology Letters》 EI CAS 2007年第2期160-163,共4页
Cyclic spectral correlation above the bifrequency plane for the received signal was calculated by the strip spectral correlation algorithm (SSCA)and then was normalized. The result was expressed by matrix. The sum o... Cyclic spectral correlation above the bifrequency plane for the received signal was calculated by the strip spectral correlation algorithm (SSCA)and then was normalized. The result was expressed by matrix. The sum of error-square was computed between corresponding elements for the theoretical sampling matrix of all kinds of modulated signals and calculated matrix. The modulation type was recognized by exploiting the minimum value of the sum of error-square. No extracted characteristic parameter and prior information are needed for identifying the modulation type compared to the conventional methods. In addition, the new method extends the recognition scope and has high recognition probability at low SNR. The simulation results obtained by means of Monter-Carlo method proved the presented algorithm. 展开更多
关键词 cyclic spectral correlation strip spectral correlation algorithm recognition perfor-mance bifrequency plane
下载PDF
Collaboration Filtering Recommendation Algorithm Based on the Latent Factor Model and Improved Spectral Clustering
8
作者 Xiaolan Xie Mengnan Qiu 《国际计算机前沿大会会议论文集》 2019年第1期98-100,共3页
Due to the development of E-Commerce, collaboration filtering (CF) recommendation algorithm becomes popular in recent years. It has some limitations such as cold start, data sparseness and low operation efficiency. In... Due to the development of E-Commerce, collaboration filtering (CF) recommendation algorithm becomes popular in recent years. It has some limitations such as cold start, data sparseness and low operation efficiency. In this paper, a CF recommendation algorithm is propose based on the latent factor model and improved spectral clustering (CFRALFMISC) to improve the forecasting precision. The latent factor model was firstly adopted to predict the missing score. Then, the cluster validity index was used to determine the number of clusters. Finally, the spectral clustering was improved by using the FCM algorithm to replace the K-means in the spectral clustering. The simulation results show that CFRALFMISC can effectively improve the recommendation precision compared with other algorithms. 展开更多
关键词 COLLABORATION FILTERING RECOMMENDATION algorithm LATENT Factor Model CLUSTER validity index spectral clustering
下载PDF
Automated Autism Spectral Disorder Classification Using Optimal Machine Learning Model
9
作者 Hanan Abdullah Mengash Hamed Alqahtani +5 位作者 Mohammed Maray Mohamed K.Nour Radwa Marzouk Mohammed Abdullah Al-Hagery Heba Mohsen Mesfer Al Duhayyim 《Computers, Materials & Continua》 SCIE EI 2023年第3期5251-5265,共15页
Autism Spectrum Disorder (ASD) refers to a neuro-disorder wherean individual has long-lasting effects on communication and interaction withothers.Advanced information technologywhich employs artificial intelligence(AI... Autism Spectrum Disorder (ASD) refers to a neuro-disorder wherean individual has long-lasting effects on communication and interaction withothers.Advanced information technologywhich employs artificial intelligence(AI) model has assisted in early identify ASD by using pattern detection.Recent advances of AI models assist in the automated identification andclassification of ASD, which helps to reduce the severity of the disease.This study introduces an automated ASD classification using owl searchalgorithm with machine learning (ASDC-OSAML) model. The proposedASDC-OSAML model majorly focuses on the identification and classificationof ASD. To attain this, the presentedASDC-OSAML model follows minmaxnormalization approach as a pre-processing stage. Next, the owl searchalgorithm (OSA)-based feature selection (OSA-FS) model is used to derivefeature subsets. Then, beetle swarm antenna search (BSAS) algorithm withIterative Dichotomiser 3 (ID3) classification method was implied for ASDdetection and classification. The design of BSAS algorithm helps to determinethe parameter values of the ID3 classifier. The performance analysis of theASDC-OSAML model is performed using benchmark dataset. An extensivecomparison study highlighted the supremacy of the ASDC-OSAML modelover recent state of art approaches. 展开更多
关键词 Autism spectral disorder machine learning owl search algorithm feature selection id3 classifier
下载PDF
Cross-spectral root-min-norm algorithm for harmonics analysis in electric power system
10
作者 裴亮 李晶 +1 位作者 曹茂永 刘世萱 《Journal of Measurement Science and Instrumentation》 CAS 2012年第1期66-69,共4页
To avoid drawbacks of classic discrete Fourier transform(DFT)method,modern spectral estimation theory was introduced into harmonics and inter-harmonics analysis in electric power system.Idea of the subspace-based root... To avoid drawbacks of classic discrete Fourier transform(DFT)method,modern spectral estimation theory was introduced into harmonics and inter-harmonics analysis in electric power system.Idea of the subspace-based root-min-norm algorithm was described,but it is susceptive to noises with unstable performance in different SNRs.So the modified root-min-norm algorithm based on cross-spectral estimation was proposed,utilizing cross-correlation matrix and independence of different Gaussian noise series.Lots of simulation experiments were carried out to test performance of the algorithm in different conditions,and its statistical characteristics was presented.Simulation results show that the modified algorithm can efficiently suppress influence of the noises,and has high frequency resolution,high precision and high stability,and it is much superior to the classic DFT method. 展开更多
关键词 electric power system inter-harmonics cross-spectral estimation singular value decomposition(SVD) subspace decomposition min-norm algorithm
下载PDF
基于孤立森林算法的弹性光网络异常流量自动识别方法 被引量:3
11
作者 李橙 何孙秦 +1 位作者 卫星 张国华 《激光杂志》 CAS 北大核心 2024年第1期179-183,共5页
弹性光网络流量传输受到时间波动导致异常,为了提高网络传输稳定性,提出基于孤立森林算法的弹性光网络异常流量自动识别算法。根据流量的异常分布特征和正常数据的差异性进行波谱密度检测,构建弹性光网络流量的谱特征提取模型,通过低通... 弹性光网络流量传输受到时间波动导致异常,为了提高网络传输稳定性,提出基于孤立森林算法的弹性光网络异常流量自动识别算法。根据流量的异常分布特征和正常数据的差异性进行波谱密度检测,构建弹性光网络流量的谱特征提取模型,通过低通滤波器卷积向量重组,实现对异常流量的谱特征筛选,采用孤立森林算法实现对网络流量异常检测的自适应寻优控制,结合多维空间结构重组方法实现对弹性光网络异常流量检测和识别。结果表明,漏检率及误检率较低,分别为3.16%,1.03%。检测用时较少,仅用16秒。在进行检测时,外部入侵率未超过1%,抗扰性较强。 展开更多
关键词 孤立森林算法 弹性光网络 异常流量 谱特征提取
原文传递
基于累积和事件段识别与改进谱聚类的锂离子电池储能系统内短路故障检测方法 被引量:1
12
作者 肖先勇 陈智凡 +2 位作者 汪颖 何涛 张逢蓉 《电网技术》 EI CSCD 北大核心 2024年第2期658-667,共10页
锂离子电池系统的内短路故障可能导致严重安全事故,其检测受到在线检测实时性以及故障特征获得性制约,是当下锂离子电池储能系统安全运行亟待解决的问题。该文提出一种基于累积和(cumulative sum,CUSUM)事件段检测与改进谱聚类的锂离子... 锂离子电池系统的内短路故障可能导致严重安全事故,其检测受到在线检测实时性以及故障特征获得性制约,是当下锂离子电池储能系统安全运行亟待解决的问题。该文提出一种基于累积和(cumulative sum,CUSUM)事件段检测与改进谱聚类的锂离子电池储能系统内短路故障检测方法。首先,考虑内短路故障时的电压/温度变化特性,基于累积和事件突变点识别方法,识别疑似内短路故障事件段。其次,构建三维故障特征,刻画检测对象内短路故障特征属性。然后,构建基于Wasserstein测度的内短路故障特征距离矩阵,检测三维空间各点稀疏特性,客观划定故障聚类,实现内短路故障检测。搭建锂离子电池内短路实验平台、建立锂离子电池电–热耦合仿真模型,算例结果表明该文方法能够准确识别疑似内短路故障事件段,在不同串并联形式及故障类型下实现故障检测,证明了该文方法的正确性与可行性。 展开更多
关键词 内短路故障检测 事件段检测 故障特征 Wasserstein距离 改进谱聚类算法
原文传递
谱聚类和Apriori算法在建筑坍塌事故致因组合分析中的应用 被引量:1
13
作者 李珏 蒋敏 《安全与环境学报》 CAS CSCD 北大核心 2024年第2期617-625,共9页
建筑坍塌事故是人员伤亡和经济损失较大的事故类型之一。为探究建筑坍塌事故不同致因之间的关联和相互依存关系,首先,选取国内2015—2020年231份建筑坍塌事故报告作为研究对象,借助R语言平台进行文本挖掘,得到43个致因。其次,运用Pytho... 建筑坍塌事故是人员伤亡和经济损失较大的事故类型之一。为探究建筑坍塌事故不同致因之间的关联和相互依存关系,首先,选取国内2015—2020年231份建筑坍塌事故报告作为研究对象,借助R语言平台进行文本挖掘,得到43个致因。其次,运用Python进行谱聚类,根据致因之间的关联强度对其进行聚类。最后,利用关联规则挖掘Apriori算法确定建筑坍塌事故致因之间的关键关联组合。结果表明,43个事故致因可分为5类,在每一个簇类中确定了最关键的致因组合,并提出了针对性的预防措施,为坍塌事故的预防和控制提供一种新的思路。 展开更多
关键词 安全社会工程 建筑施工 坍塌事故 文本挖掘 谱聚类 APRIORI算法
原文传递
多级冗余强干扰下医用三维力传感器数据的自动挖掘方法
14
作者 岳根霞 王剑 刘金花 《传感技术学报》 CAS CSCD 北大核心 2024年第8期1383-1388,共6页
针对医用三维力传感器容易受电磁场等外部环境的影响,产生大量相似特征数据,导致其输出紊乱信号,降低传感器控制精度和测量速度的问题,提出一种多级冗余强干扰下三维力传感器数据挖掘方法。根据角度标定理论采集三维力传感器冗余数据;... 针对医用三维力传感器容易受电磁场等外部环境的影响,产生大量相似特征数据,导致其输出紊乱信号,降低传感器控制精度和测量速度的问题,提出一种多级冗余强干扰下三维力传感器数据挖掘方法。根据角度标定理论采集三维力传感器冗余数据;引入相似度指数函数计算冗余因子,获取三维力传感器冗余数据活跃度,完成数据冗余分类;通过差值去噪算法高性能过滤三维力传感器冗余数据;利用谱聚类算法构建拉普拉斯矩阵,剔除冗余数据,实现三维力传感器数据自动挖掘。仿真结果表明,所提方法在多级冗余强干扰下的三维力传感器控制精度为96.54%,测量速度为0.61 ms,能量消耗为0.26 kcal。由此证明,所提方法的控制精度高、测量速度快、传输效果优,能够满足机器人辅助手术过程中的力反馈控制需求。 展开更多
关键词 三维力传感器 冗余数据 数据挖掘 角度标定 指数函数 差值去噪 谱聚类算法
下载PDF
航拍多光谱田间秸秆覆盖量反演模型的建立与优化
15
作者 刘媛媛 孙宇 +4 位作者 高雪冰 王利斌 王跃勇 刘梦琪 崔舒然 《光学精密工程》 EI CAS CSCD 北大核心 2024年第11期1773-1787,共15页
保护性耕作是农业耕地可持续性发展的重要方法,已被世界多地采用,秸秆覆盖量实现从“有无”到“多少”的进一步判定,是秸秆还田检测的重要指标。通过无人机搭载多光谱相机航拍研究区内春秋两季遥感数据,并同步测定玉米秸秆覆盖量。首先... 保护性耕作是农业耕地可持续性发展的重要方法,已被世界多地采用,秸秆覆盖量实现从“有无”到“多少”的进一步判定,是秸秆还田检测的重要指标。通过无人机搭载多光谱相机航拍研究区内春秋两季遥感数据,并同步测定玉米秸秆覆盖量。首先,通过遥感数据提取光谱反射率并构建光谱指数,采用相关系数法筛选出对秸秆覆盖量敏感的波段变量和光谱变量,作为模型输入变量;然后,采用支持向量机(Support Vector Machine,SVM)、随机森林(Random Forest,RF)、BP神经网络(Back Propagation Neural Network,BPNN)和极限学习机(Extreme Learning Machine,ELM)4种机器学习算法,建立玉米秸秆覆盖量的反演模型,比较不同时期和不同研究区域的模型精度;最后,为解决预测性能受其模型参数影响较大问题,引入遗传算法(Genetic Algorithm,GA)和粒子群算法(Particle Swarm Optimization,PSO),并提出遗传-粒子群混合算法(Genetic-Particle Swarm Optimization,GA-PSO),利用它们的互补性提高模型的性能,完成区域内秸秆覆盖量的估算。实验结果表明,基于GA-PSO优化的RF算法玉米秸秆覆盖量反演模型取得了最佳的反演效果,其中R^(2)达到了0.74。同时,对比分析不同数据的反演结果,均较为真实地反映了区域内秸秆覆盖量,估测准确率达到91.36%,说明可以通过优化模型实现结果估算。研究为保护性耕作秸秆还田量检测提供科学参考,亦为其他作物秸秆覆盖量估测提供了可靠的模型反演方法。 展开更多
关键词 多光谱图像 机器学习 秸秆覆盖量 无人机 遗传算法 粒子群算法
下载PDF
基于改进粒子群算法优化的染色木材颜色检测算法研究
16
作者 管雪梅 吴言 杨渠三 《林产工业》 北大核心 2024年第1期1-7,共7页
为提高染色木材颜色的检测精度和速度,对樟子松木材单板进行染色,选取染色单板的光谱反射率作为输入,以极限学习机模型为基础构建预测模型,对染色单板的色度参数L^(*)、a^(*)、b^(*)进行预测,运用粒子群算法对ELM权值和阈值进行寻优,并... 为提高染色木材颜色的检测精度和速度,对樟子松木材单板进行染色,选取染色单板的光谱反射率作为输入,以极限学习机模型为基础构建预测模型,对染色单板的色度参数L^(*)、a^(*)、b^(*)进行预测,运用粒子群算法对ELM权值和阈值进行寻优,并引入非线性惯性权重和新的位置与速度更新策略改进粒子群算法,以消除其易陷入局部最优的缺点。此外,以L^(*)、a^(*)、b^(*)平均绝对误差为评价指标,与基础ELM模型及其他模型作对比,发现优化后的模型平均绝对误差为0.16,测色效果相较于基础ELM的0.68、麻雀算法优化的ELM的0.37等具有明显优势,这对于提高木材染色生产效率具有重要意义。 展开更多
关键词 粒子群算法 极限学习机 反射率 惯性权重 全局优化
下载PDF
基于谱聚类的主动配电网多时间尺度无功优化策略
17
作者 闫丽梅 丁泽华 《浙江电力》 2024年第2期58-68,共11页
高比例分布式光伏接入配电网后,传统优化方案无法有效平抑电压波动,分布式光伏逆变器的无功调控能力难以充分利用。为此,提出一种基于谱聚类的主动配电网多时间尺度无功优化策略,该方法分为日前优化和日内实时优化两个阶段。首先,对离... 高比例分布式光伏接入配电网后,传统优化方案无法有效平抑电压波动,分布式光伏逆变器的无功调控能力难以充分利用。为此,提出一种基于谱聚类的主动配电网多时间尺度无功优化策略,该方法分为日前优化和日内实时优化两个阶段。首先,对离散设备的时间耦合性进行解耦,以配电网网损、平均电压偏差、电压波动严重程度为目标函数,建立基于社交网络搜索算法的日前无功优化模型,确定离散设备静态最优档位序列;其次,通过谱聚类的方法进行耦合,确定离散设备动态最优档位序列,结合改进的分布式光伏逆变器就地控制策略,建立日内实时优化模型,从而抑制日前预测数据偏差导致的电压波动;最后,基于改进后的IEEE33节点系统进行仿真实验。仿真结果表明,所提策略可以有效降低运算难度、提高求解效率,验证了该策略的有效性和优越性。 展开更多
关键词 主动配电网 多时间尺度 动态无功优化 谱聚类解耦方法 社交网络搜索算法
下载PDF
拉曼光谱结合光谱特征区间筛选算法快速定量鉴别植物调和油品质 被引量:1
18
作者 吴升德 姜鑫 +2 位作者 李爱琴 郭志明 朱家骥 《食品科学》 EI CAS CSCD 北大核心 2024年第6期244-253,共10页
本研究提出了一种基于拉曼光谱与光谱特征区间筛选算法实现植物调和油中高价值植物油含量快速定量检测的方法。首先,将粒子群优化(particle swarm optimization,PSO)算法与灰狼优化(grey wolf optimization,GWO)算法融合构建混合智能优... 本研究提出了一种基于拉曼光谱与光谱特征区间筛选算法实现植物调和油中高价值植物油含量快速定量检测的方法。首先,将粒子群优化(particle swarm optimization,PSO)算法与灰狼优化(grey wolf optimization,GWO)算法融合构建混合智能优化算法,即PSOGWO算法。其次,将PSOGWO与组合移动窗口(combined moving window,CMW)策略结合构建新型的拉曼光谱特征区间筛选算法,即PSOGWO-CMW算法。然后,将玉米油(corn oil,CO)和特级初榨橄榄油(extra virgin olive oil,EVOO)以不同比例配制为CO-EVOO植物调和油,并采集其拉曼光谱。将拉曼光谱输入偏最小二乘回归、PSO-CMW、GWO-CMW和PSOGWO-CMW模型预测EVOO含量,并比较建模效果。结果表明,PSOGWO-CMW模型具有最佳的预测性能。采用本方法与气相色谱-质谱法分别检测真实的CO-EVOO植物调和油样本中EVOO含量,结果表明两者的检测性能无显著差异。本方法快速、准确,亦可用于其他植物调和油中高价值植物油含量的快速定量检测。 展开更多
关键词 拉曼光谱 植物调和油 智能优化算法 光谱特征区间筛选 定量鉴别
下载PDF
The Chebyshev spectral element method using staggered predictor and corrector for elastic wave simulations 被引量:3
19
作者 车承轩 王秀明 林伟军 《Applied Geophysics》 SCIE CSCD 2010年第2期174-184,195,共12页
Based on strong and weak forms of elastic wave equations, a Chebyshev spectral element method (SEM) using the Galerkin variational principle is developed by discretizing the wave equation in the spatial and time dom... Based on strong and weak forms of elastic wave equations, a Chebyshev spectral element method (SEM) using the Galerkin variational principle is developed by discretizing the wave equation in the spatial and time domains and introducing the preconditioned conjugate gradient (PCG)-element by element (EBE) method in the spatial domain and the staggered predictor/corrector method in the time domain. The accuracy of our proposed method is verified by comparing it with a finite-difference method (FDM) for a homogeneous solid medium and a double layered solid medium with an inclined interface. The modeling results using the two methods are in good agreement with each other. Meanwhile, to show the algorithm capability, the suggested method is used to simulate the wave propagation in a layered medium with a topographic traction free surface. By introducing the EBE algorithm with an optimized tensor product technique, the proposed SEM is especially suitable for numerical simulation of wave propagations in complex models with irregularly free surfaces at a fast convergence rate, while keeping the advantage of the finite element method. 展开更多
关键词 Chebyshev spectral element element by element predictor/corrector algorithm
下载PDF
基于Hilbert包络谱熵和GA-SVM的水轮发电机轴承故障诊断 被引量:2
20
作者 陈培演 孙晓 +2 位作者 欧立涛 于柳 陈元健 《机电工程技术》 2024年第3期199-204,共6页
水轮发电机轴承在运行时承受着整体机组的轴向负荷与复杂水推力,针对其产生的非稳态、非线性特征的振动信号,提出一种基于Hilbert包络谱分析与遗传算法支持向量机(GA-SVM)相结合的诊断方法,用于轴承故障状态的识别。首先对推力轴承运行... 水轮发电机轴承在运行时承受着整体机组的轴向负荷与复杂水推力,针对其产生的非稳态、非线性特征的振动信号,提出一种基于Hilbert包络谱分析与遗传算法支持向量机(GA-SVM)相结合的诊断方法,用于轴承故障状态的识别。首先对推力轴承运行时产生的振动信号进行集合经验模态分解(Ensemble Empirical Mode Decomposition,EEMD),分解成若干个固有模态函数(Intrinsic Mode Function,IMF),依据峭度准则选取主要IMF分量并通过Hilbert包络谱分析,计算包络谱熵,将归一化后的包络谱熵作为特征向量输入GA-SVM进行训练与故障识别。仿真实验结果表明,基于EEMD包络谱熵分析法相比于时频域图像处理能更好地提取出复杂工况下的故障信号特征,遗传算法支持向量机识别准确率达96.87%,该算法模型可进一步应用于水轮发电机轴承故障诊断。 展开更多
关键词 水轮发电机 轴承故障诊断 集合经验模态分解 Hilbert包络谱熵 遗传算法支持向量机
下载PDF
上一页 1 2 50 下一页 到第
使用帮助 返回顶部