Misclassification analysis of discriminant model

This paper extends the criterion of the misclassification ratio of discriminant model and presents a new selection method of discriminant model.For selecting the discriminant model,this method establishes the rule of misclassification degree ratio through misclassification ratio of the discriminant model and misclassification degree of the samples.To test the effect of this method,this work uses seven UCI data sets.Numerical experiments on these examples indicate that this method has certain rationality and has a better effect to select a discriminant model.

A Multi-Task Motion Generation Model that Fuses a Discriminator and a Generator

The human motion generation model can extract structural features from existing human motion capture data,and the generated data makes animated characters move.The 3D human motion capture sequences contain complex spatial-temporal structures,and the deep learning model can fully describe the potential semantic structure of human motion.To improve the authenticity of the generated human motion sequences,we propose a multi-task motion generation model that consists of a discriminator and a generator.The discriminator classifies motion sequences into different styles according to their similarity to the mean spatial-temporal templates from motion sequences of 17 crucial human joints in three-freedom degrees.And target motion sequences are created with these styles by the generator.Unlike traditional related works,our model can handle multiple tasks,such as identifying styles and generating data.In addition,by extracting 17 crucial joints from 29 human joints,our model avoids data redundancy and improves the accuracy of model recognition.The experimental results show that the discriminator of the model can effectively recognize diversified movements,and the generated data can correctly fit the actual data.The combination of discriminator and generator solves the problem of low reuse rate of motion data,and the generated motion sequences are more suitable for actual movement.

Fisher discriminant analysis model and its application for prediction of classification of rockburst in deep-buried long tunnel

A Fisher discriminant analysis (FDA) model for the prediction of classification of rockburst in deep-buried long tunnel was established based on the Fisher discriminant theory and the actual characteristics of the project.First, the major factors of rockburst,such as the maximum tangential stress of the cavern wall σ_θ, uniaxial compressive strength σ_c, uniaxial tensile strength σ_t, and the elastic energy index of rock W_(et), were taken into account in the analysis.Three factors, Stress coefficient σ_θlσ_c, rock brittleness coefficient σ_c/σ_t, and elastic energy index W_(et), were defined as the criterion indices for rockburst prediction in the proposed model.After training and testing of 12 sets of measured data, the discriminant functions of FDA were solved, and the ratio of misdiscrimination is zero.Moreover, the proposed model was used to predict rockbursts of Qinling tunnel along Xi'an-Ankang railway.The results show that three forecast results are identical with the actual situation.Therefore, the prediction accuracy of the FDA model is acceptable.

Water resistant features of high-risk outburst coal seams and standard discriminant model of mining under water-pressure

It is important to emphasize the value of research in safe mining technology of high-risk water outburst coal seams. We describe briefly current conditions abroad and in China. Based on an Ordovician limestone aquifer with high-risk water outburst seams in the Feicheng coal field, we analyzed the water-resistant characteristics of a coal floor aquifuge and the behavior of water head intrusion of a confined aquifer and propose a safe criterion model and relevant technology of mining above aquifers. This has brought satisfactory results in engineering practice.

Discriminant Analysis of Liquor Brands Based on Moving-Window Waveband Screening Using Near-Infrared Spectroscopy

Partial least squares discriminant analysis (PLS-DA) with integrated moving-window (MW) waveband screening was applied to the discriminant analysis of liquor brands with near-infrared (NIR) spectroscopy. Luzhou Laojiao, a popular liquor with strong fragrant flavor, was used as the identified liquor brand (160 samples, negative, 52 vol alcoholicity). Liquors of 10 other brands with strong fragrant flavor were used as the interferential brands (200 samples, positive, 52 vol alcoholicity). The Kennard-Stone algorithm was used for the division of modeling samples to achieve uniformity and representativeness. Based on the MW-PLS-DA, a simplified optimal model set with 157 wavebands was further proposed. This set contained five types of wavebands corresponding to the NIR absorption bands of water, ethanol, and other micronutrients (i.e., acids, aldehydes, phenols, and aromatic compounds) in liquor for practical choice. Using five selected simple models with 4775 - 4239, 7804 - 6569, 6264 - 5844, 9435 - 7896, and 12066 - 10373 cm-1, the validation recognition rates were obtained as 99.3% or higher. Results show good prediction performance and low model complexity, and also provided a valuable reference for designing small dedicated instruments. The proposed method is a promising tool for large-scale inspection of liquor food safety.

Adaptive Object Tracking Discriminate Model for Multi-Camera Panorama Surveillance in Airport Apron

Autonomous intelligence plays a significant role in aviation security.Since most aviation accidents occur in the take-off and landing stage,accurate tracking of moving object in airport apron will be a vital approach to ensure the operation of the aircraft safely.In this study,an adaptive object tracking method based on a discriminant is proposed in multi-camera panorama surveillance of large-scale airport apron.Firstly,based on channels of color histogram,the pre-estimated object probability map is employed to reduce searching computation,and the optimization of the disturbance suppression options can make good resistance to similar areas around the object.Then the object score of probability map is obtained by the sliding window,and the candidate window with the highest probability map score is selected as the new object center.Thirdly,according to the new object location,the probability map is updated,the scale estimation function is adjusted to the size of real object.From qualitative and quantitative analysis,the comparison experiments are verified in representative video sequences,and our approach outperforms typical methods,such as distraction-aware online tracking,mean shift,variance ratio,and adaptive colour attributes.

Entity Burst Discriminative Model for Cumulative Citation Recommendation

Knowledge base acceleration-cumulative citation recommendation(KBA-CCR)aims to detect citation-worthiness documents from a chronological stream corpus for a set of target entities in a knowledge base.Most previous works only consider a number of semantic features between documents and target entities in the knowledge base,and then use powerful machine learning approaches such as logistic regression to classify relevant documents and non-relevant documents.However,the burst activities of an entity have been proved to be a significant signal to predict potential citations.In this paper,an entity burst discriminative model(EBDM)is presented to substantially exploit such burst features.The EBDM presents a new temporal representation based on the burst features,which can capture both temporal and semantic correlations between entities and documents.Meanwhile,in contrast to the bag-of-words model,the EBDM can significantly decrease the number of non-zero entries of feature vectors.An extensive set of experiments were conducted on the TREC-KBA-2012 dataset.The results show that the EBDM outperforms the performance of the state-of-the-art models.

Effects of Differential Item Discriminations between Individual-Level and Cluster-Level under the Multilevel Item Response Theory Model

This study attempted to interpret differential item discriminations between individual and cluster levels by focusing on patterns and magnitudes of item discriminations under 2PL multilevel IRT model through a set of variety simulation conditions. The consistency between the mean of individual-level ability estimates and cluster-level ability estimates was evaluated by the correlations between them. As a result, it was found that they were highly correlated if the patterns of item discriminations were the same for both individual and cluster levels. The magnitudes of item discriminations themselves did not affect much on correlations, as far as the patterns were the same at the two levels. However, it was found that the correlation became lower when the patterns of item discriminations were different between the individual and cluster levels. Also, it was revealed that the mean of the estimated individual-level abilities would not be necessarily a good representation of the cluster-level ability, if the patterns were different at the two levels.

Performance of real‑time neutron/gamma discrimination methods

Nuclear security usually requires the simultaneous detection of neutrons and gamma rays.With the development of crystalline materials in recent years,Cs2LiLaBr6(CLLB)dual-readout detectors have attracted extensive attention from researchers,where real-time neutron/gamma pulse discrimination is the critical factor among detector performance parameters.This study investigated the discrimination performance of the charge comparison,amplitude comparison,time comparison,and pulse gradient_(m)ethods and the effects of a Sallen–Key filter on their performance.Experimental results show that the figure of merit(FOM)of all four methods is improved by proper filtering.Among them,the charge comparison method exhibits excellent noise resistance;moreover,it is the most_(s)uitable method of real-time discrimination for CLLB detectors.However,its discrimination performance depends on the parameters t_(s),t_(m),and t_(e).When t_(s)corresponds to the moment at which the pulse is at 10%of its peak value,t_(e)requires a delay of only 640–740 ns compared to t_(s),at which time the potentially optimal FOM of the charge comparison method at 3.1–3.3 MeV is greater than 1.46.The FOM obtained using the t_(m)value calculated by a proposed maximized discrimination difference model(MDDM)and the potentially optimal FOM differ by less than 3.9%,indicating that the model can provide good guidance for parameter selection in the charge comparison method.

Prognostic and diagnostic scoring models in acute alcoholassociated hepatitis:A review comparing the performance of different scoring systems

Alcohol-associated hepatitis(AAH)is a severe form of liver disease caused by alcohol consumption.In the absence of confounding factors,clinical features and laboratory markers are sufficient to diagnose AAH,rule out alternative causes of liver injury and assess disease severity.Due to the elevated mortality of AAH,assessing the prognosis is a radical step in management.The Maddrey discriminant function(MDF)is the first established clinical prognostic score for AAH and was commonly used in the earliest AAH clinical trials.A MDF>32 indicates a poor prognosis and a potential benefit of initiating corticosteroids.The model for end stage liver disease(MELD)score has been studied for AAH prognostication and new evidence suggests MELD may predict mortality more accurately than MDF.The Lille score is usually combined to MDF or MELD score after corticosteroid initiation and offers the advantage of assessing response to treatment a 4-7 d into the course.Other commonly used scores include the Glasgow Alcoholic Hepatitis Score and the Age Bilirubin international normalized ratio Creatinine model.Clinical AAH correlate adequately with histologic severity scores and leave little indication for liver biopsy in assessing AAH prognosis.AAH presenting as acute on chronic liver failure(ACLF)is so far prognosticated with ACLF-specific scoring systems.New artificial intelligence-generated prognostic models have emerged and are being studied for use in AAH.Acute kidney injury(AKI)is one possible complication of AAH and is significantly associated with increased AAH mortality.Predicting AKI and alcohol relapse are important steps in the management of AAH.The aim of this review is to discuss the performance and limitations of different scoring models for AAH mortality,emphasize the most useful tools in prognostication and review predictors of recurrence.

基于太赫兹成像检测技术与特征提取方法结合巴旦木饱满度检测方法研究

巴旦木是一种营养丰富的坚果,对巴旦木的品质进行检测具有重要的经济价值和实际意义。由于巴旦木具有较为坚硬的外壳,传统的检测手段较难实现内部检测,因此,采用新兴的太赫兹透射成像检测技术,开展巴旦木饱满度的检测研究。首先采集不同饱满度巴旦木的太赫兹透射图像,并且从太赫兹图像的感兴趣区域分别提取无样品区域、空壳区域和满仁区域的太赫兹光谱信息;为了提高模型的精度,减少计算量,采用竞争性自适应重加权算法(CARS)、无信息变量消除(UVE)、连续投影算法(SPA)、蒙特卡罗无信息变量消除法(MCUVE)和遗传算法(GA)对太赫兹光谱信息进行特征提取,建立对应的最小二乘支持向量机(LS-SVM)、随机森林(RF)和K-近邻(KNN)定性判别模型,对巴旦木的饱满和空壳区域进行检测和鉴别。此外,对太赫兹特征图像转为JPG格式,接着转化为RGB格式进行G通道提取和图像二值化分离出外壳和果仁图像,检测饱满度为太赫兹特征图像的壳仁像素点之比;对原始图像进行轮廓提取和图像二值化分离出外壳和果仁图像,实际饱满度为原始图像的壳仁像素点之比。通过计算检测饱满度和实际饱满度的误差,证明了太赫兹透射成像技术检测巴旦木饱满度的可行性。建立的KS-GA-RF模型的鉴别效果最优,准确率为98.21%;通过壳仁像素点之比分别计算出对应的检测饱满度和实际饱满度,误差为16%。研究验证了采用太赫兹图、谱相融合的方法,可以很好地实现对巴旦木内部种仁饱满度可视化检测,为巴旦木的准确分级提供了新的思路,也为太赫兹成像技术检测其他坚果饱满度提供了理论参考,具有重要的应用价值。

基于LDA-MURE模型的背景音乐自适应推荐方法

用户的情绪状态不同,需要的背景音乐也不同,因此提出基于LDA-MURE模型的背景音乐自适应推荐方法。提取背景音乐的音频特征和社会化标签,通过Fisher线性判别分析方法融合上述数据的特征,结合投影变换方法获得不同类别背景音乐的类内离散度和类间离散度。通过现代心理学分析人类情绪的节律周期变化,在此基础上判断用户当前的情绪状态。最后在LDA模型的基础上构建LDA-MURE模型,为用户推荐不同类别的背景音乐。实验结果表明,所提方法的MEA指标值较低、P@N指标值较高、用户满意度较高。

艾滋病感染者抑郁症状相关因素分析的统计模型

目的:运用3种统计模型分析育龄期女性HIV感染者抑郁症状的相关因素并进行比较。方法:选取育龄期女性HIV感染者553人,采用汉密顿抑郁量表(HAMD)评估感抑郁症状,选取logistic回归模型、人工神经网络模型、决策树模型分析抑郁症状的相关因素,采用ROC曲线比较3种模型的预测效果。结果:ROC曲线下面积由大到小依次排序为决策树模型、人工神经网络模型和logistic回归模型(AUC=0.813、0.707、0.701),两两比较显示,人工神经网络模型、logistic回归模型的ROC面积值均小于决策树模型的ROC面积值(均P<0.01)。结论:在预测HIV感染者抑郁症状方面,决策树模型的效果要优于人工神经网络模型和logistic回归模型。

基于Fisher判别分析可分性信息融合的马铃薯VC含量高光谱检测方法

为提高马铃薯VC含量检测结果的准确性和可靠性,提出一种基于Fisher判别分析(Fisher discriminant analysis,FDA)可分性数据融合的检测模型输入变量构建方法。首先,利用高光谱成像技术采集200个马铃薯的高光谱信息,通过对比6种预处理方法和原始数据的建模结果,确定多元散射校正为光谱数据的预处理方法;其次,采用竞争性自适应重加权采样(competitive adaptive reweighted sampling,CARS)、连续投影算法(successive projections algorithm,SPA)及CARS-SPA组合算法3种方法提取相应特征波长,通过对比分析最终确定34个有效特征波长;然后,将有效特征波长进行FDA可分性数据融合,根据融合的新变量对样本间差异性判别能力的大小进行筛选,确定构建检测模型的输入变量;最后,分别对FDA融合前后筛选的变量建立偏最小二乘模型和反向传播神经网络(back propagation neural network,BPNN)模型,并对检测结果进行对比分析。结果表明,将CARS算法提取的34个特征波长进行FDA融合,采用前3个融合变量作为构建检测模型的输入变量时,其所建BPNN模型的相关系数由0.9726提高至0.9990,均方根误差由0.7723降低至0.1727,不仅能够极大地降低数据分析维度,而且能够提高检测结果的准确性。因此,基于FDA可分性数据融合构建检测模型输入变量可以提高马铃薯VC含量检测结果的准确性。

一类基于模糊推理的具有机动自适应的目标跟踪算法

针对变结构多模型算法在机动目标跟踪中对目标机动不确定性、量测不确定性自适应能力不足的问题,提出一种基于模糊推理的机动自适应目标跟踪算法.设计一种基于模糊推理的双级机动判别模型,利用模型概率信息和主模型滤波残差加权范数进行主模型可信度和机动判别推理;并将双级机动判别引入基于可能模型集的期望模式扩增方法(EMA-LMS)框架,提出一种模糊推理EMA-LMS算法,实现对模型集自适应的参数和策略的在线调节,从而生成更加接近目标真实运动模式的期望模型,并更好地对模型进行取舍.仿真结果表明,本文算法能够有效增强算法对目标机动和量测不确定的自适应性,提高跟踪精度.

农作物生长的胁迫因素光谱甄别模型研究

玉米作为中国重要的粮食产物之一,其生长期间的健康检测一直是农业生产的重要问题。以受不同因素影响下生长的玉米叶片为研究对象,采用ASD光谱仪进行叶片光谱采集;对原始光谱数据进行导数(derivative,D)处理,针对经过求导后光谱部分数据无限趋向0的现象,引入压缩感知(compressed sensing,CS)方法,并采用迭代重加权最小二乘(iterative re-weighted least squares,IRLS)数据重建的方法对光谱数据进行恢复;然后选取竞争性自适应重加权算法(competitive adapative reweighted sampling,CARS),结合不同试验下的影响因素作为标签提取光谱特征;最后通过多层感知机分类模型(multi-layer perceptron,MLP),以达到判别生长状态不佳的农作物所受影响因素的目的。本次试验生成的D-CS-CARS-MLP模型的精度相较于传统模型精度有所提高,可以高达99%以上,可以看出该模型可以针对农作物生长状态不佳所受的影响因素进行判别。经过验证,D-CS-CARS-MLP模型具有较好的稳定性和精度,为植被健康生长监测提供了新的思路与方法。

茯砖茶感官特征分析及其产地判别模型构建研究

为客观准确地评价不同产地茯砖茶感官特征品质,结合感官审评、化学组分检测、化学计量学等研究茯砖茶感官品质特征及不同产地茯砖茶判别模型构建。结果表明:湖南、浙江、陕西等19个茯砖茶因原料物质基础的不同其感官品质有非常明显的差异。其中,茯砖茶滋味得分(taste score, TS)与咖啡碱(caffeine, CAF)、水浸出物(water leachate, WL)、儿茶素(catechin, CAT)和表儿茶素(epicatechin, EC)呈现出显著相关性,其相关系数(P<0.05)分别为0.81、0.62、0.55、0.50。同时,基于化学组分的主成分(PCA)表明,前4个主成分的累计方差贡献率为79.48%,并以前4个主成分的线性回归方程和贡献率构建了茯砖茶感官品质综合评价模型与产地判别模型。正交偏最小二乘法判别分析(OPLA-DA)显示,19个不同产地的茯砖茶样品被明显地划分为3组,评价模型对不同产地茯砖茶识别度较高。采用交叉验证法对模型进行验证,模型对自变量的拟合指数(R~2X)为0.879,对因变量的拟合指数(R~2Y)为0.992,预测指数(Q^(2))为0.53。经OPLS-DA共识别出6种预测变量重要性投影(VIP)值大于1的差异指标,其中茶多酚(tea polyphenols, TPP)、可溶性糖(soluble sugar, SS)、CAF、WL为茯砖茶感官特征标志性差异品质成分。结果表明,应用感官审评、化学组分检测、化学计量学等方法可以实现茯砖茶感官特征及其不同产地茯砖茶的快速、准确判别,同时也为茯砖茶感官特征及其不同产地判别提供一种新的参考方法。

多视图专家组区域建议预测的视觉跟踪

为解决大多数最新的目标跟踪器都面临着判别特征表示缺乏多样性、目标定位过于模糊以及正样本的数量要求问题,提出一种基于多视图的顶层特征的区域建议网络的跟踪预测学习算法。融合多种视图的特征表示方式,利用丰富多样的语义信息,有效解决判别特征过于单一的问题。在扩展的边界框上构建多个支持向量机模型并加入区域建议网络模块,精确优化边界框,预测最优的目标位置,缓解目标定位过于模糊和正样本的数量有限的问题。通过大量视频基准序列对方法的综合评价,其结果表明,提出方法融合了轻量化的深度学习模型和多视图专家组的优点,使跟踪性能有了显著提升。

低程度风化火山岩风化壳结构划分与主控因素——以准噶尔盆地西缘车排子凸起石炭系火山岩为例

为解决低风化程度的火山岩风化壳结构划分及火山岩油气储层评价与预测的难题,利用研究区28口井岩心、录井测井和地震资料,对车排子凸起石炭系火山岩风化壳的岩石学、矿物学、地球化学、储层物性进行系统研究。结果表明:研究区岩石整体风化程度偏低。在此基础上提出一种将风化壳自上而下分为土壤带、水解带、淋滤带、崩解带、蚀变带、母岩带的6层划分方案。利用研究区玄武安山岩的自然电位、自然伽马、声波、电阻率4种测井数据,结合过采样算法的决策树模型对淋滤带、崩解带、蚀变带进行分类判别,准确率达87.8%。综合分析认为:低风化程度火山岩风化壳有效储层厚度、结构带发育程度、横纵向分布等具有非均质性;有利储层发育主要受古地貌和断裂作用的控制,淋滤带、崩解带是主要有利储层发育区,常分布于古地貌的斜坡地带,一般厚度在350 m以内;受断裂作用影响,风化壳有效储层厚度可达450 m。

基于近红外光谱的烤烟油分识别研究

【目的】对烤烟油分等级进行科学预测,实现不同油分档次烤烟的快速光谱鉴别。【方法】对代表性植烟县的299份全叶位覆盖的不同油分档次云烟87烟叶样本进行近红外光谱采集,利用一阶导数(D1)、归一化(NOR)、小波变换(WAVE)、标准正态化(SNV)和多元散射校正(MSC)共5种方法对光谱数据预处理后,考察了线性的偏最小二乘判别分析(PLS-DA)和非线性的最小二乘支持向量机(LS-SVM)判别模型的判别效果。【结果】对近红外原始光谱数据进行主成分降维后,所构建的PLS-DA油分档次分类模型训练集的准确率可达100.0%,但测试集仅有79.8%,经过D1、NOR、SNV和MSC预处理后,模型的测试集准确率分别提高到了85.9%、90.0%、83.8%和83.8%;基于对近红外原始光谱数据直接构建的LS-SVM油分档次分类模型的训练集准确率也达100.0%,测试集达到92.9%,经过NOR、WAVE、SNV和MSC预处理后测试集的准确率均提高到了95.0%以上,以MSC预处理的99.0%的准确率最高。【结论】多元散射校正预处理结合LS-SVM法构建的油分档次判别模型效果最好,提高了烤烟油分判定效率。