Objective classification and analysis of vegetation data

A program package is described in which vegetation data can be objectively classified and analysed. Classification is based on minimum entropy. Results show that in a comparison with TWINSPAN, improvements to the relevé sequence, in terms of community variation, can be obtained. Furthermore, TWINSPAN classifications are shown to be dependent on a particular relevé input sequence.     

Computational methods for gene expression-based tumor classification

Gene expression profiles may offer more or additional information than classic morphologic- and histologic-based tumor classification systems. Because the number of tissue samples examined is usually much smaller than the number of genes examined, efficient data reduction and analysis methods are critical. In this report, we propose a principal component and discriminant analysis method of tumor classification using gene expression profile data. Expression of 2000 genes in 40 tumor and 22 normal colon tissue samples is used to examine the feasibility of gene expression-based tumor classification systems. Using this method, the percentage of correctly classified normal and tumor tissue was 87.0%. The combined approach using principal components and discriminant analysis provided superior sensitivity and specificity compared to an approach using simple differences in the expression levels of individual genes.     

Evaluation of electromyography normalisation methods for the back squat

The aim of the study was to evaluate maximal isometric (dynamometer based {MVC-NORM} and isometric squat {MIS-NORM}) and sub-maximal EMG normalisation methods (60%-NORM, 70%-NORM, 80%-NORM) for dynamic back squat exercise (DSQ-EX). The absolute reliability (limits of agreement {LOA}, coefficient of variation {CV%}), relative reliability (intra-class correlation coefficient {ICC}) and sensitivity of each method was assessed. Ten resistance-trained males attended four sessions. Session one assessed maximum back squat strength (three repetition maximum {3RM}). In the remaining three sessions Vastus lateralis (VL) and Bicep femoris (BF) EMG were measured whilst participants completed normalisation tasks and DSQ-EX sets at 65%, 75%, 85% and 95% of 3RM. MIS-NORM produced lower intra-participant CV% compared to MVC-NORM. 80%-NORM produced lower intra-participant CV% than other sub-maximal methods for VL and BF during eccentric and concentric phases. 80%-NORM also produced narrower 95% LOA results than all other normalisation methods. The MIS-NORM method displayed higher ICC values for both muscles during eccentric and concentric phases. The 60%-NORM and 70%-NORM methods were the most sensitive for VL and BF during eccentric and concentric phases. Only normalisation methods for the concentric action of the VL enhanced sensitivity compared to unnormalised EMG. Overall, dynamic normalisation methods demonstrated better absolute reliability and sensitivity for reporting VL and BF EMG within the current study compared to maximal isometric methods.     

Statistical methods for classification of human chromosomes.

The basic technical facts of human cytogenetics and the laboratory methods employed in chromosome research are explained in simple terms. The main variables used to describe chromosome images are defined and discussed. Three discriminant analysis models for chromosome classification are developed: one in which each chromosome is classified in isolation, a modification in which the cell, if normal, contains 2 chromosomes of each of the 23 kinds, and a final one in which the cell is the unit of analysis instead of the chromosome. Suggestions are made to reduce the calculations involved and to take into account missing chromosomes. The problem of detection and classification of aberrative chromosomes is studied, also in relation to multiple cell analysis. Finally four relevant problems are briefly discussed: selection of metaphase spreads, selection of variables, uncertain reference classification and measurement of performance.     

Assessment of tumor vascularization: immunohistochemical and non-invasive methods

Growth of solid tumors beyond a certain mass is dependent on the vascular bed from pre-existing host vasculature. The process of angiogenesis is essential not only for primary tumor growth but also for metastasis. The number of microvessels within the invasive component of a primary tumor reflects the degree of tumor angiogenesis. At present the most widely used method to assess neovascularization is the quantitation of intratumoral microvessel density (IMD) by immunohistochemical methods in which specific markers for endothelial cells are employed. In this paper we analyze the different methods used to assess IMD, as well as their advantages and potential methodological pitfalls. Several studies have shown a close correlation between IMD, tumor growth and the occurrence of metastasis, suggesting that IMD is a prognostic indicator of clinical relevance. Furthermore, preliminary studies suggest that determination of angiogenesis may predict responsiveness to some forms of conventional anticancer therapy. Although the histological microvessel density technique is the current gold standard to characterize tumor angiogenesis, it may not be the ideal tool for clinical purposes because it needs to be performed on biopsy material and does not assess the functional pathways involved in the angiogenic activity of tumors. Non-invasive assessment of tumor vascularity is possible in vivo by means of Doppler sonography, dynamic contrast-enhanced magnetic resonance imaging (MRI) and positron emission tomography (PET). These methods may be preferable to histological assay because they are non-invasive, survey the entire tumor, reflect both anatomic and physiologic characteristics, and may be useful to monitor the activity of antiangiogenic therapies.     

A comparison of two non-invasive methods for measuring scapular orientation in functional positions

Identification of scapular dyskinesis and evaluation of interventions depend on the ability to properly measure scapulothoracic (ST) motion. The most widely used measurement approach is the acromion marker cluster (AMC), which can yield large errors in extreme humeral elevation and can be inaccurate in children and patient populations. Recently, an individualized regression approach has been proposed as an alternative to the AMC. This technique utilizes the relationship between ST orientation, humerothoracic orientation and acromion process position derived from calibration positions to predict dynamic ST orientations from humerothoracic and acromion process measures during motion. These individualized regressions demonstrated promising results for healthy adults; however, this method had not yet been compared to the more conventional AMC. This study compared ST orientation estimates by the AMC and regression approaches to static ST angles determined by surface markers placed on palpated landmarks in typically developing adolescents performing functional tasks. Both approaches produced errors within the range reported in the literature for skin-based scapular measurement techniques. The performance of the regression approach suffered when applied to positions outside of the range of motion in the set of calibration positions. The AMC significantly underestimated ST internal rotation across all positions and overestimated posterior tilt in some positions. Overall, root mean square errors for the regression approach were smaller than the AMC for every position across all axes of ST motion. Accordingly, we recommend the regression approach as a suitable technique for measuring ST kinematics in functional motion.     

Molecular methods for the detection and classification of Cryptosporidium

Cryptosporidiosis is a zoonotic disease caused by a parasitic protozoan belonging to the coccidial genus Cryptosporidium. Current laboratory methods are adequate for the detection of the infection when oocysts are present in great numbers, but more-sensitive means of identification are urgently required. In a recent issue of Parasitology Today, Carolyn Petersen has presented a review of the cell biology of this parasite'. Here, Kath Webster draws attention to the various methods involved in its detection and classification.     

Prediction of human core body temperature using non-invasive measurement methods

The measurement of core body temperature is an efficient method for monitoring heat stress amongst workers in hot conditions. However, invasive measurement of core body temperature (e.g. rectal, intestinal, oesophageal temperature) is impractical for such applications. Therefore, the aim of this study was to define relevant non-invasive measures to predict core body temperature under various conditions. We conducted two human subject studies with different experimental protocols, different environmental temperatures (10 °C, 30 °C) and different subjects. In both studies the same non-invasive measurement methods (skin temperature, skin heat flux, heart rate) were applied. A principle component analysis was conducted to extract independent factors, which were then used in a linear regression model. We identified six parameters (three skin temperatures, two skin heat fluxes and heart rate), which were included for the calculation of two factors. The predictive value of these factors for core body temperature was evaluated by a multiple regression analysis. The calculated root mean square deviation (rmsd) was in the range from 0.28 °C to 0.34 °C for all environmental conditions. These errors are similar to previous models using non-invasive measures to predict core body temperature. The results from this study illustrate that multiple physiological parameters (e.g. skin temperature and skin heat fluxes) are needed to predict core body temperature. In addition, the physiological measurements chosen in this study and the algorithm defined in this work are potentially applicable as real-time core body temperature monitoring to assess health risk in broad range of working conditions.     

Objective and automatic classification of Parkinson disease with Leap Motion controller

Background

The main objective of this paper is to develop and test the ability of the Leap Motion controller (LMC) to assess the motor dysfunction in patients with Parkinson disease (PwPD) based on the MDS-UPDRSIII exercises. Four exercises (thumb forefinger tapping, hand opening/closing, pronation/supination, postural tremor) were used to evaluate the characteristics described in MDS-UPDRSIII. Clinical ratings according to the MDS/UPDRS-section III items were used as target. For that purpose, 16 participants with PD and 12 healthy people were recruited in Ospedale Cisanello, Pisa, Italy. The participants performed standardized hand movements with camera-based marker. Time and frequency domain features related to velocity, angle, amplitude, and frequency were derived from the LMC data.

Results

Different machine learning techniques were used to classify the PD and healthy subjects by comparing the subjective scale given by neurologists against the predicted diagnosis from the machine learning classifiers. Feature selection methods were used to choose the most significant features. Logistic regression (LR), naive Bayes (NB), and support vector machine (SVM) were trained with tenfold cross validation with selected features. The maximum obtained classification accuracy with LR was 70.37%; the average area under the ROC curve (AUC) was 0.831. The obtained classification accuracy with NB was 81.4%, with AUC of 0.811. The obtained classification accuracy with SVM was 74.07%, with AUC of 0.675.

Conclusions

Results revealed that the system did not return clinically meaningful data for measuring postural tremor in PwPD. In addition, it showed limited potential to measure the forearm pronation/supination. In contrast, for finger tapping and hand opening/closing, the derived parameters showed statistical and clinical significance. Future studies should continue to validate the LMC as updated versions of the software are developed. The obtained results support the fact that most of the set of selected features contributed significantly to classify the PwPD and healthy subjects.

     

小麦抗旱生态分类中适合性聚类方法的研究

探索了适合于小麦品种抗旱生态分类的聚类方法。选用２１个农艺性状和１５个冬小麦品种（系）,在聚类分析的各环节上,通过采用不同的策略,大规模进行了各种分类结果的比较。结果表明,在与专家经验分类接近程度上,数据转换方法中,原始数据法依次大于普通相关阵基础上的方差极大正交旋转法、Ｐｒｏｍａｘ斜交旋转法、主成份法;相似性度量上,欧氏距离大于马氏距离;聚类方式上,对应分析法和模糊聚类法大于最短距离法、最长距离     

Effective dimension reduction methods for tumor classification using gene expression data

MOTIVATION: One particular application of microarray data, is to uncover the molecular variation among cancers. One feature of microarray studies is the fact that the number n of samples collected is relatively small compared to the number p of genes per sample which are usually in the thousands. In statistical terms this very large number of predictors compared to a small number of samples or observations makes the classification problem difficult. An efficient way to solve this problem is by using dimension reduction statistical techniques in conjunction with nonparametric discriminant procedures. RESULTS: We view the classification problem as a regression problem with few observations and many predictor variables. We use an adaptive dimension reduction method for generalized semi-parametric regression models that allows us to solve the 'curse of dimensionality problem' arising in the context of expression data. The predictive performance of the resulting classification rule is illustrated on two well know data sets in the microarray literature: the leukemia data that is known to contain classes that are easy 'separable' and the colon data set.     

A comparative study of feature selection and multiclass classification methods for tissue classification based on gene expression

This paper studies the problem of building multiclass classifiers for tissue classification based on gene expression. The recent development of microarray technologies has enabled biologists to quantify gene expression of tens of thousands of genes in a single experiment. Biologists have begun collecting gene expression for a large number of samples. One of the urgent issues in the use of microarray data is to develop methods for characterizing samples based on their gene expression. The most basic step in the research direction is binary sample classification, which has been studied extensively over the past few years. This paper investigates the next step-multiclass classification of samples based on gene expression. The characteristics of expression data (e.g. large number of genes with small sample size) makes the classification problem more challenging. The process of building multiclass classifiers is divided into two components: (i) selection of the features (i.e. genes) to be used for training and testing and (ii) selection of the classification method. This paper compares various feature selection methods as well as various state-of-the-art classification methods on various multiclass gene expression datasets. Our study indicates that multiclass classification problem is much more difficult than the binary one for the gene expression datasets. The difficulty lies in the fact that the data are of high dimensionality and that the sample size is small. The classification accuracy appears to degrade very rapidly as the number of classes increases. In particular, the accuracy was very low regardless of the choices of the methods for large-class datasets (e.g. NCI60 and GCM). While increasing the number of samples is a plausible solution to the problem of accuracy degradation, it is important to develop algorithms that are able to analyze effectively multiple-class expression data for these special datasets.     

Nonlinear methods for discrimination and their application to classification of protein structures

Discriminant analysis assigns objects to one of several classes on the basis of attributes which characterize the objects. The success of classification depends on the selection of discriminatory attributes and on the choice of an assignment rule. In this paper we focus on the latter and discuss ways to obtain nonlinear classification rules through maximum likelihood, canonical components and projection pursuit. We use both linear and nonlinear methods to classify proteins into three secondary structural types: alpha, beta, and mixed alpha and beta or irregular. Using simple attributes, dependent on amino acid properties, we show that the rate of incorrect classification can be decreased by more than 15% when nonlinear methods are used.     

Comparison of three different methods for automated classification of cervical cells.

Over 4600 exfoliated squamous cervical cells taken from appropriate Papanicolaou samples were classified as normal, mildly dysplastic, moderately dysplastic and severely dysplastic by an experienced cytopathologist. The slides were de-stained and subsequently re-stained with Feulgen Thionin-SO2 stain. Images of the nuclei were then captured, recorded and processed employing an image cytometry device. Automated classification of the cells was carried out using three different methods--discriminant function analysis, a decision tree classifier and a neutral network classifier. The discriminant function analysis method, which combined all dysplastic cells into an abnormal group, achieved a combined error rate of less than 0.4% for moderate and severe dysplastic cells, and less than 40% for mildly dysplastic cells. All three methods yielded comparable results, which approached those of human performance.     

Comparison of classification methods for detecting associations between SNPs and chick mortality

Multi-category classification methods were used to detect SNP-mortality associations in broilers. The objective was to select a subset of whole genome SNPs associated with chick mortality. This was done by categorizing mortality rates and using a filter-wrapper feature selection procedure in each of the classification methods evaluated. Different numbers of categories (2, 3, 4, 5 and 10) and three classification algorithms (naïve Bayes classifiers, Bayesian networks and neural networks) were compared, using early and late chick mortality rates in low and high hygiene environments. Evaluation of SNPs selected by each classification method was done by predicted residual sum of squares and a significance test-related metric. A naïve Bayes classifier, coupled with discretization into two or three categories generated the SNP subset with greatest predictive ability. Further, an alternative categorization scheme, which used only two extreme portions of the empirical distribution of mortality rates, was considered. This scheme selected SNPs with greater predictive ability than those chosen by the methods described previously. Use of extreme samples seems to enhance the ability of feature selection procedures to select influential SNPs in genetic association studies.     

Penalized discriminant methods for the classification of tumors from gene expression data

Due to the advent of high-throughput microarray technology, it has become possible to develop molecular classification systems for various types of cancer. In this article, we propose a methodology using regularized regression models for the classification of tumors in microarray experiments. The performances of principal components, partial least squares, and ridge regression models are studied; these regression procedures are adapted to the classification setting using the optimal scoring algorithm. We also develop a procedure for ranking genes based on the fitted regression models. The proposed methodologies are applied to two microarray studies in cancer.