应用新的基于知识编码方法及双层SVM识别人类PolⅡ启动子

目的优选对人类RNA聚合酶(Pol)Ⅱ启动子数据识别分类并提高识别准确率的方法。方法采用基于知识的统计编码方法、CpG编码、五联体(Pentamers)编码、模式字典(Pattern Dictionary)编码,最后建立共识模型,使用支持向量机(SVM)方法对启动子数据进行分类。结果启动子数据编码后在SVM中识别,与其他利用SVM工具相比,得到了较高的识别准确率、特异性及灵敏度。将新编码方法应用到人类22号染色体启动子数据的识别中,其中模式字典编码识别准确率达到了90.98%。结论共识模型考虑了各子模型的独立性和模型之间的差异性,发挥了各模型之间的互补优势,从而提高了最终的识别准确率。     

Automated classification of neonatal sleep states using EEG

Objective

To develop a method for automated neonatal sleep state classification based on EEG that can be applied over a wide range of age.

A learning method for the class imbalance problem with medical data sets

In medical data sets, data are predominately composed of “normal” samples with only a small percentage of “abnormal” ones, leading to the so-called class imbalance problems. In class imbalance problems, inputting all the data into the classifier to build up the learning model will usually lead a learning bias to the majority class. To deal with this, this paper uses a strategy which over-samples the minority class and under-samples the majority one to balance the data sets. For the majority class, this paper builds up the Gaussian type fuzzy membership function and α-cut to reduce the data size; for the minority class, we use the mega-trend diffusion membership function to generate virtual samples for the class.Furthermore, after balancing the data size of classes, this paper extends the data attribute dimension into a higher dimension space using classification related information to enhance the classification accuracy. Two medical data sets, Pima Indians’ diabetes and the BUPA liver disorders, are employed to illustrate the approach presented in this paper. The results indicate that the proposed method has better classification performance than SVM, C4.5 decision tree and two other studies.     

基于SVM的尿液粒子识别算法研究

本文将支持向量机的算法引入到尿沉渣有形成分的分类问题上.在提取特征的基础上,采用交叉验证法和精度等高线图进行核函数及参数的选择.根据支持向量机和数据集特点,设计出由两级分类器集成的支持向量机多分类器.得到了相应的混淆矩阵.临床实验数据分类评测以及与神经网络方法比较结果表明,提出的算法具有一定的优势.     

Support vector machines committee classification method for computer-aided polyp detection in CT colonography

RATIONALE AND OBJECTIVES: A new classification scheme for the computer-aided detection of colonic polyps in computed tomographic colonography is proposed. MATERIALS AND METHODS: The scheme involves an ensemble of support vector machines (SVMs) for classification, a smoothed leave-one-out (SLOO) cross-validation method for obtaining error estimates, and use of a bootstrap aggregation method for training and model selection. Our use of an ensemble of SVM classifiers with bagging (bootstrap aggregation), built on different feature subsets, is intended to improve classification performance compared with single SVMs and reduce the number of false-positive detections. The bootstrap-based model-selection technique is used for tuning SVM parameters. In our first experiment, two independent data sets were used: the first, for feature and model selection, and the second, for testing to evaluate the generalizability of our model. In the second experiment, the test set that contained higher resolution data was used for training and testing (using the SLOO method) to compare SVM committee and single SVM performance. RESULTS: The overall sensitivity on independent test set was 75%, with 1.5 false-positive detections/study, compared with 76%-78% sensitivity and 4.5 false-positive detections/study estimated using the SLOO method on the training set. The sensitivity of the SVM ensemble retrained on the former test set estimated using the SLOO method was 81%, which is 7%-10% greater than the sensitivity of a single SVM. The number of false-positive detections per study was 2.6, a 1.5 times reduction compared with a single SVM. CONCLUSION: Training an SVM ensemble on one data set and testing it on the independent data has shown that the SVM committee classification method has good generalizability and achieves high sensitivity and a low false-positive rate. The model selection and improved error estimation method are effective for computer-aided polyp detection.     

Recognition of Motor Imagery Electroencephalography Using Independent Component Analysis and Machine Classifiers

Motor imagery electroencephalography (EEG), which embodies cortical potentials during mental simulation of left or right finger lifting tasks, can be used to provide neural input signals to activate a brain computer interface (BCI). The effectiveness of such an EEG-based BCI system relies on two indispensable components: distinguishable patterns of brain signals and accurate classifiers. This work aims to extract two reliable neural features, termed contralateral and ipsilateral rebound maps, by removing artifacts from motor imagery EEG based on independent component analysis (ICA), and to employ four classifiers to investigate the efficacy of rebound maps. Results demonstrate that, with the use of ICA, recognition rates for four classifiers (fisher linear discriminant (FLD), back-propagation neural network (BP-NN), radial-basis function neural network (RBF-NN), and support vector machine (SVM)) improved significantly, from 54%, 54%, 57% and 55% to 70.5%, 75.5%, 76.5% and 77.3%, respectively. In addition, the areas under the receiver operating characteristics (ROC) curve, which assess the quality of classification over a wide range of misclassification costs, also improved from .65, .60, .62, and .64 to .74, .76, .80 and .81, respectively.     

二进制量子粒子群优化算法及其在化工过程故障诊断中的应用

针对实际化工生产过程中故障数据缺乏,采用适合小样本问题的支持向量机(SVM)对化工过程稳态故障进行诊断。为了保证在线故障诊断的实时性,消除高维监控数据以及系统噪声对故障诊断的干扰,提出了一种新的基于二进制量子粒子群优化(BQPSO)算法和SVM的故障特征选择方法。仿真实验表明:BQPSO算法具有良好的全局搜索能力,能够快速、准确地搜索到故障特征变量;而基于特征选择的SVM故障诊断方法能可靠地实现对复杂化工过程的在线故障诊断。     

Predictive learning with structured (grouped) data

Many applications of machine learning involve sparse and heterogeneous data. For example, estimation of diagnostic models using patients’ data from clinical studies requires effective integration of genetic, clinical and demographic data. Typically all heterogeneous inputs are properly encoded and mapped onto a single feature vector, used for estimating a classifier. This approach, known as standard inductive learning, is used in most application studies. Recently, several new learning methodologies have emerged. For instance, when training data can be naturally separated into several groups (or structured), we can view model estimation for each group as a separate task, leading to a Multi-Task Learning framework. Similarly, a setting where the training data are structured, but the objective is to estimate a single predictive model (for all groups), leads to the Learning with Structured Data and SVM+ methodology recently proposed by Vapnik [(2006). Empirical inference science afterword of 2006. Springer]. This paper describes a biomedical application of these new data modeling approaches for modeling heterogeneous data using several medical data sets. The characteristics of group variables are analyzed. Our comparisons demonstrate the advantages and limitations of these new approaches, relative to standard inductive SVM classifiers.     

In silico prediction of rhabdomyolysis of compounds by self-organizing map and support vector machine

Rhabdomyolysis is a potentially lethal syndrome resulting in leakage of myocyte intracellular contents into the plasma. Some drugs, such as lipid-lowering drugs and antihistamines, can cause rhabdomyolysis. In this work, a dataset containing 186 chemical compounds causing rhabdomyolysis and 117 drugs not causing rhabdomyolysis was collected. The dataset was split into a training set (containing 230 compounds) and a test set (containing 73 compounds). A Kohonen’s self-organizing map (SOM) and a support vector machine (SVM) were applied to develop classification models to differentiate compounds causing and not causing rhabdomyolysis. Using the SOM method, classification accuracies of 93.3% for the training set and 84.5% for the test set were achieved; using the SVM method, classification accuracies of 95.2% for the training set and 84.9% for the test set were achieved. In addition, the extended connectivity fingerprints (ECFP_4) for all the molecules were calculated and analyzed to find the important features of molecules relating to rhabdomyolysis.     

孔隙度方法在肝癌超声图像纹理特征分类中的性能评估

介绍和评估了描述肝癌超声图像纹理特征的孔隙度方法.用14幅正常肝和14幅原发性肝癌图像为样本,将用5种方法得到的正常肝和原发性肝癌图像的孔隙度值进行正态分布检验,5种方法孔隙度值基本都呈正态分布.只有用立方盒质量和盒柱平均值法得到的正常肝和原发性肝癌的孔隙度平均值通过了差异显著性Student-t检验,用这两种方法得到的正常肝孔隙度值有较小的平均值和标准差,原发性肝癌图像孔隙度值有较大的平均值和标准差.对用5种方法得到的孔隙度进行ROC分析结果表明盒柱平均值法得到了最大的ROC曲线下的面积为0.959 2.用10折交叉验证和不同核函数的SVM进行分类,立方盒质量和盒柱平均值法分别得到了96.428 6％和92.857 1％的分类正确率.实验结果表明所提出的盒柱平均值法具有较强的描述肝癌超声图像纹理特征的能力.