蛾翅数学形态特征用于夜蛾分类和鉴定的可行性研究

摘要: 为探讨蛾翅数学形态特征(MMC)在夜蛾科分类鉴定中的可行性, 本文利用数字化技术获得和处理昆虫图像, 对鳞翅目夜蛾科6种夜蛾的右前翅提取矩形度、 延长度、 叶状性、 偏心率、 球状性、 似圆度和不变矩Hu1、 Hu2等13项与大小尺度和方向均无关的数学形态特征, 并利用方差分析、 逐步判别分析和聚类分析等方法研究了各项数学形态特征在昆虫分类上作为分类特征的可行性、 可靠性和重要性, 并且从数学形态学角度对夜蛾科6个种的亲缘关系进行了分析。分析结果认为矩形度和延长度2个形态特征对这6种夜蛾的分类鉴定没有显著意义, 从而筛选出11个形态特征作为分类变量, 它们的作用大小依次为： （偏心率、 Hu5、 Hu7）＞Hu2＞似圆度＞球状性＞Hu3＞（叶状性、 Hu1、 Hu6）＞Hu4。利用蛾翅的这些特征参数成功地实现了对夜蛾科6种夜蛾的分类鉴定, 基于这些特征参数的6种夜蛾的亲缘关系远近与基于传统形态学的系统进化观点相同。研究表明蛾翅数学形态特征可应用于蛾类昆虫的快速鉴定, 为未来逐步实现蛾类昆虫的自动识别奠定了基础。     

主成分分析法用于西洋参样品分类研究

建立西洋参药材分类方法;采用电感耦合等离子体质谱(ICP-MS)法对12个西洋参样品中的15种无机元素的含量进行测定,用高效液相色谱(HPLC)法测定上述样品中的7种人参皂苷的含量,用蒽酮-硫酸法测定其中多糖的含量;进而采用主成分分析法(PCA)对所测得的西洋参样品的23个变量进行分类研究;12个西洋参样品能得到合理的分类,而各人参皂苷的含量是决定西洋参样品分类的第1关键因素,元素Mn、Cu、As、Ni、Mo以及多糖的含量是第2关键因素;主成分分析法是西洋参分析分类的有效方法。     

用主成分分析法分析金翅夜蛾亚科各性状对分类的重要性和性状变异方向

本文在“金翅夜蛾亚科的数值分类研究”的基础上用主成分分析的结果对金翅夜蛾亚科分类的性状做进一步分析,说明各性状对分类的重要性和性状的变异方向,并对用协方差矩阵和相关矩阵进行的主成分分析结果进行比较,说明对本问题（分类指标全是定性指标）适宜用协方差矩阵做主成分分析。     

数学形态学在昆虫总科阶元分类学上的应用研究

对鳞翅目Lepidoptera和鞘翅目Coleoptera 5个总科23种昆虫图像中提取昆虫面积、周长等11项数学形态特征进行了粗糙集神经网络分析,并与赵汗青统计分析加以比较,结果表明在总科阶元上,11项特征的可靠性顺序为面积、亮斑数＞周长、横轴长、形状参数、圆形性、似圆度、偏心率＞纵轴长、叶状性、球状性形性、似圆度、偏心率)＞(纵轴长、叶状性)＞(形状参数、亮斑数).与赵汗青等人用统计学分析的结果不完全一致,但大多数属性特征重要性还是一致的.神经网络模式识别结果与传统分类结果完全一致.由此得出:粗糙集理论在昆虫依据数学形态特征进行分类方面与统计分析方法相比更为理想.     

中国原产石蒜属植物的数量分类和主成分分析

应用数量分类学方法对中国原产石蒜属13种2变种的35个性状进行Q、R聚类分析和主成分分析,探讨国产石蒜属植物种间的亲缘关系,并对分类性状进行评价。研究结果显示,Q型聚类可分为2个大类和8小类,安徽石蒜与长筒石蒜的亲缘关系很近,认为将其作为长筒石蒜的变种更为合适,同时支持玫瑰石蒜、红蓝石蒜、乳白石蒜、江苏石蒜、稻草石蒜的杂交起源观点。R型聚类可分为7个组;经主成分分析,35个性状可综合为5个主成分,其累积贡献率达82.55%,根据这5个主成分与性状间的相关性,选出影响比较大的16个性状,其中鳞茎形状、花被片宽和雄蕊长/花被片长的比值最为重要,可作为大类群划分的依据,而花被片是否具条纹、花丝颜色、花色、花葶粗、幼叶尖端及边缘颜色、种子有无等可作为物种划分的重要依据。     

山东省木瓜主栽品种的数量分类及主成分分析

依据16个形态性状,对山东省主栽的20个木瓜 (Chaenomeles spp. )品种进行了UPGMA聚类分析和主成分分析,并对16个形态性状间的相关性进行了检验.聚类分析结果表明,在欧氏距离1.058处可将20个品种分为皱皮木瓜[C. speciosa (Sweet) Nakai]和木瓜[C. sinensis (Thouin) Koehne]2组;在欧氏距离0.743处,皱皮木瓜组可进一步分为浓香型(包括'一品香'和'金香')和淡香型(包括'罗扶'、'长俊'、'红霞'、'玉佛'和'奥星')2个品种群;木瓜组可进一步分为大果型(包括'玉兰'和'豆青')和中小果型(包括'细皮'、'剩花'、'手瓜'、'佛手'、'金苹果'、'大金苹果'、'大狮子头'、'小狮子头'、'陈香'、'红云'和'可食')2个品种群.果实贮藏后果皮是否变皱、果实表面有无棱沟、嫩叶颜色、结果枝是否带刺、托叶形状等性状之间的相关性极显著, 相关系数均达到 1.000 0.主成分分析结果表明,前4个主成分的累积贡献率达到89.66%,根据前4个主成分中各性状的绝对权重值,筛选出对木瓜品种分类影响较大的12个性状,其中果实贮藏后果皮是否变皱、果实表面有无棱沟、嫩叶颜色、结果枝是否带刺和托叶形状5个性状可作为区分山东省20个木瓜主栽品种的主要形态性状依据.     

基于主成分特征投影法建立利用16S rRNA基因序列进行物种分类方法的研究

提出一种有别于系统发育树的根据16S rRNA基因序列进行物种分类的新方法。首先将基因的碱基字母形式转换成数字形式,构建多维向量。然后根据主成分分析方法将该向量向数据分布最大方向投影,将原数据用几个“主成分”线性表出,而不丢失原数据的信息,采用主成分的显示功能作出三维主成分特征投影视图,达到分类的目的。在双歧杆菌和肠球菌的分类识别中得到较好的应用。     

西花蓟马分类鉴定方法的研究进展

西花蓟马FranklinieUa occidentalis(Pergande)是一种危险性外来人侵害虫,虫体小,鉴定困难.本文总结了国内外西花蓟马分类鉴定方法的研究进展,包括形态学鉴别、分子生物学方法以及基于表皮碳氢化合物分析的生化分类方法,并讨论了各种分类方法的优势和弊端,最后对西花蓟马的分类研究前景进行了展望.     

鹅膏属真菌形态特征的主成分与聚类分析

本研究选取了《中国真菌志·第二十七卷·鹅膏科》中27个物种及变种,对这些分类单元的菌托形状、菌褶颜色、担子大小等形态学特征进行统计,依据这些形态学特征进行主成分和聚类分析,得到各物种及变种与各个形态学特征之间的关联程度。通过聚类分析将27个物种及变种分为四大类,最终结果与鹅膏属分类情况一致,验证了上述分析方法在鹅膏属分类研究领域具有可行性与准确性。     

基于主成分分析的随机森林视网膜OCT图像分层算法研究

视网膜是层状结构,临床上可以根据视网膜层厚度改变对一些疾病进行预测和诊断.为了快速且准确地分割出视网膜的不同层带,本论文提出一种基于主成分分析的随机森林视网膜光学相干断层扫描技术(optical coherence tomography,OCT)图像分层算法.该方法使用主成分分析(principal component analysis,PCA)法对随机森林采集到的特征进行重采样,保留重采样后权重大的特征信息维度,从而消除特征维度间的关联性和信息冗余.结果表明,总特征维度在29维的情况下,保留前18维度训练速度提高了23.20%,14维度训练速度提高了42.38%,而对图像分割精度方面影响较小,实验表明该方法有效地提高了算法的效率.     

基于人工神经网络的昆虫鸣声识别

以常见的7种飞虱雄虫求偶鸣声信号的频率峰值作为输入向量,用人工神经网络来识别它们的鸣声,平均识别率达90．6％。人工神经网络可以用于昆虫鸣声识别。     

A Stock Market Forecasting Model Combining Two-Directional Two-Dimensional Principal Component Analysis and Radial Basis Function Neural Network

In this paper, we propose and implement a hybrid model combining two-directional two-dimensional principal component analysis ((2D)²PCA) and a Radial Basis Function Neural Network (RBFNN) to forecast stock market behavior. First, 36 stock market technical variables are selected as the input features, and a sliding window is used to obtain the input data of the model. Next, (2D)²PCA is utilized to reduce the dimension of the data and extract its intrinsic features. Finally, an RBFNN accepts the data processed by (2D)²PCA to forecast the next day''s stock price or movement. The proposed model is used on the Shanghai stock market index, and the experiments show that the model achieves a good level of fitness. The proposed model is then compared with one that uses the traditional dimension reduction method principal component analysis (PCA) and independent component analysis (ICA). The empirical results show that the proposed model outperforms the PCA-based model, as well as alternative models based on ICA and on the multilayer perceptron.     

Artificial Neural Network Method for Predicting the Specificity of GalNAc-transferase

The specificity of GalNAc-transferase is consistent with the existence of an extended site composed of nine subsites, denoted by R₄, R₃, R₂, R₁, R₀, R₁, R₂, R₃, and R₄, where the acceptor at R₀ is either Ser or Thr to which the reducing monosaccharide is anchored. To predict whether a peptide will react with the enzyme to form a Ser- or Thr-conjugated glycopeptide, a neural network method—Kohonen's self-organization model is proposed in this paper. Three hundred five oligopeptides are chosen for the training site, with another 30 oligopeptides for the test set. Because of its high correct prediction rate (26/30=86.7%) and stronger fault-tolerant ability, it is expected that the neural network method can be used as a technique for predicting O-glycosylation and designing effective inhibitors of GalNAc-transferase. It might also be useful for targeting drugs to specific sites in the body and for enzyme replacement therapy for the treatment of genetic disorders.     

FT-IR Spectroscopy and Artificial Neural Network Identification of Fusarium Species

A rapid spectroscopic approach for whole‐organism fingerprinting of Fourier transform infrared (FT‐IR) spectroscopy was used to analyse 16 isolates from five closely related species of Fusarium: F. graminearum, F. moniliforme, F. nivale, F. semitectum and F. oxysporum. Principal components analysis and hierarchical cluster analysis were used to study the clusters in the data. On visual inspection of the clusters from both methods, the spectra were not differentiated into five separate clusters corresponding to species and these unsupervised methods failed to identify these fungal strains. When the data were trained by back propagation algorithm of artificial neural networks (ANNs) with principal components scores of spectra used as input modes, the strains were accurately predicted and recognized. The results in this study show that FT‐IR spectroscopy in combination with principal component artificial neural networks (PC‐ANNs) is well suited for identifying Fusarium spp. It would be advantageous to establish a comprehensive database of taxonomically well‐defined Fusarium species to aid the identification of unknown strains.     

翅脉的数学形态特征在蝴蝶分类鉴定中的应用研究

能否量化地利用翅脉特征对鳞翅目昆虫进行种类鉴定,这是近年发展起来的数字化昆虫分类鉴定研究中具有创新性的课题。本文使用化学方法去除蝴蝶翅面的鳞片和色斑,通过扫描获取到蝴蝶翅脉图片,利用DrawWing软件对7种蝴蝶前翅内部翅脉交点坐标进行了自动获取。通过计算相邻两点间的距离,利用单变量方差分析和典则判别分析,证明粉蝶科4个属的蝴蝶每个参数对结果都有影响,而绢蝶属3种蝴蝶翅脉交点2~3、7~8和9~1间的距离对其本身的判别无影响。通过分层聚类分析,绢蝶属的3种蝴蝶被聚为一类,在传统昆虫分类学中,它们的关系也最近。此外,通过与半自动提取软件TPSDig提取的数据进行比较,从另一个侧面证明了通过比较翅脉交点间的距离对蝴蝶进行分类鉴定研究具有参考意义。     

Research on Plant Species Identification Based on Improved Convolutional Neural Network

Plant species recognition is an important research area in image recognition in recent years. However, the existing plant species recognition methods have low recognition accuracy and do not meet professional requirements in terms of recognition accuracy. Therefore, ShuffleNetV2 was improved by combining the current hot concern mechanism, convolution kernel size adjustment, convolution tailoring, and CSP technology to improve the accuracy and reduce the amount of computation in this study. Six convolutional neural network models with sufficient trainable parameters were designed for differentiation learning. The SGD algorithm is used to optimize the training process to avoid overfitting or falling into the local optimum. In this paper, a conventional plant image dataset TJAU10 collected by cell phones in a natural context was constructed, containing 3000 images of 10 plant species on the campus of Tianjin Agricultural University. Finally, the improved model is compared with the baseline version of the model, which achieves better results in terms of improving accuracy and reducing the computational effort. The recognition accuracy tested on the TJAU10 dataset reaches up to 98.3%, and the recognition precision reaches up to 93.6%, which is 5.1% better than the original model and reduces the computational effort by about 31% compared with the original model. In addition, the experimental results were evaluated using metrics such as the confusion matrix, which can meet the requirements of professionals for the accurate identification of plant species.     

Mathematical Modeling of the Reduction of Safranin onto Chemically Modified Rice Husks in Stirred Tank Reactor Using Response Surface Methodology and Artificial Neural Network

ABSTRACT

The effluents coming from the dye industries are colored and polluted, and the disposal of these wastes into receiving waters causes damage to the water as well as the environment. The use of rice husk for the removal of dye from wastewater has been explored in a stir tank reactor. The effects of operation variables such as adsorbent dosage, contact time, dye concentration, initial pH, and agitation on the removal of safranin were investigated in a stirred tank reactor. The combined effect of various process parameters on dye removal were analyzed using response surface methodology (RSM), and the modeling of the process parameter had been done using the artificial neural network simulation method. It was observed that response surface methodology can determine the optimization of the process parameters and the model derived from the simulation of the artificial neural network (ANN) (deviation from experimental results was ～0.09%) described the process variable efficiently. It was observed that at the initial solution pH of 6.28 and adsorbent dosage of 15.63 g L^?1, dye removal of safranin was 97%.     

Cross-Talk Correction Method for Knee Kinematics in Gait Analysis Using Principal Component Analysis (PCA): A New Proposal

Background

In 3D gait analysis, the knee joint is usually described by the Eulerian way. It consists in breaking down the motion between the articulating bones of the knee into three rotations around three axes: flexion/extension, abduction/adduction and internal/external rotation. However, the definition of these axes is prone to error, such as the “cross-talk” effect, due to difficult positioning of anatomical landmarks. This paper proposes a correction method, principal component analysis (PCA), based on an objective kinematic criterion for standardization, in order to improve knee joint kinematic analysis.

Methods

The method was applied to the 3D gait data of two different groups (twenty healthy subjects and four with knee osteoarthritis). Then, this method was evaluated with respect to three main criteria: (1) the deletion of knee joint angle cross-talk (2) the reduction of variance in the varus/valgus kinematic profile (3) the posture trial varus/valgus deformation matching the X-ray value for patients with knee osteoarthritis. The effect of the correction method was tested statistically on variabilities and cross-talk during gait.

Results

Cross-talk was lower (p<0.05) after correction (the correlation between the flexion-extension and varus-valgus kinematic profiles being annihilated). Additionally, the variance in the kinematic profile for knee varus/valgus and knee flexion/extension was found to be lower and higher (p<0.05), respectively, after correction for both the left and right side. Moreover, after correction, the posture trial varus/valgus angles were much closer to x-ray grading.

Conclusion

The results show that the PCA correction applied to the knee joint eliminates the cross-talk effect, and does not alter the radiological varus/valgus deformation for patients with knee osteoarthritis. These findings suggest that the proposed correction method produces new rotational axes that better fit true knee motion.     

Support Vector Machine and Artificial Neural Network Models for the Classification of Grapevine Varieties Using a Portable NIR Spectrophotometer

The identification of different grapevine varieties, currently attended using visual ampelometry, DNA analysis and very recently, by hyperspectral analysis under laboratory conditions, is an issue of great importance in the wine industry. This work presents support vector machine and artificial neural network’s modelling for grapevine varietal classification from in-field leaf spectroscopy. Modelling was attempted at two scales: site-specific and a global scale. Spectral measurements were obtained on the near-infrared (NIR) spectral range between 1600 to 2400 nm under field conditions in a non-destructive way using a portable spectrophotometer. For the site specific approach, spectra were collected from the adaxial side of 400 individual leaves of 20 grapevine (Vitis vinifera L.) varieties one week after veraison. For the global model, two additional sets of spectra were collected one week before harvest from two different vineyards in another vintage, each one consisting on 48 measurement from individual leaves of six varieties. Several combinations of spectra scatter correction and smoothing filtering were studied. For the training of the models, support vector machines and artificial neural networks were employed using the pre-processed spectra as input and the varieties as the classes of the models. The results from the pre-processing study showed that there was no influence whether using scatter correction or not. Also, a second-degree derivative with a window size of 5 Savitzky-Golay filtering yielded the highest outcomes. For the site-specific model, with 20 classes, the best results from the classifiers thrown an overall score of 87.25% of correctly classified samples. These results were compared under the same conditions with a model trained using partial least squares discriminant analysis, which showed a worse performance in every case. For the global model, a 6-class dataset involving samples from three different vineyards, two years and leaves monitored at post-veraison and harvest was also built up, reaching a 77.08% of correctly classified samples. The outcomes obtained demonstrate the capability of using a reliable method for fast, in-field, non-destructive grapevine varietal classification that could be very useful in viticulture and wine industry, either global or site-specific.     

The Use of Artificial Neural Networks for Species Identification of Aegilops Based on Analysis of D Genomes

The possibilities of the use of artificial neural networks (ANNs) for identification of some polyploid species of genus Aegilopsbased on the idiograms of theirDgenomes were demonstrated.