A review of near infrared spectroscopy and chemometrics in pharmaceutical technologies

Near-infrared spectroscopy (NIRS) is a fast and non-destructive analytical method. Associated with chemometrics, it becomes a powerful tool for the pharmaceutical industry. Indeed, NIRS is suitable for analysis of solid, liquid and biotechnological pharmaceutical forms. Moreover, NIRS can be implemented during pharmaceutical development, in production for process monitoring or in quality control laboratories.This review focuses on chemometric techniques and pharmaceutical NIRS applications. The following topics are covered: qualitative analyses, quantitative methods and on-line applications. Theoretical and practical aspects are described with pharmaceutical examples of NIRS applications.     

Combined entropy based method for detection of QRS complexes in 12-lead electrocardiogram using SVM

A method based on signal entropy is proposed for the detection of QRS complexes in the 12-lead electrocardiogram (ECG) using support vector machine (SVM). Digital filtering techniques are used to remove power line interference and base line wander in the ECG signal. Combined Entropy criterion was used to enhance the QRS complexes. SVM is used as a classifier to delineate QRS and non-QRS regions. The performance of the proposed algorithm was tested using 12-lead real ECG recordings from the standard CSE ECG database. The numerical results indicated that the algorithm achieved 99.93% of detection rate. The percentage of false positive and false negative is 0.54% and 0.06%, respectively. The proposed algorithm performs better as compared with published results of other QRS detectors tested on the same database.     

基于小波变换和Teager能量算子的癫痫脑电自动分类

提出一种利用小波变换和能量算子对EEG进行预处理提取癫痫特征信号,进行近似熵估计,对脑电信号进行分类的新方法。首先利用小波分析将EEG信号进行4层分解分成多个子频带,对频率接近棘波的第1,2层小波系数计算非线性能量算子,再对能量算子进行近似熵估计,最后用SVM对EEG信号进行分类。结果表明,该方法对癫痫发作期EEG和正常的EEG分类效果比较理想。     

MSCT孤立肺小结节的神经网络模型的应用研究分析

目的研究神经网络模型（SVM）在MSCT孤立肺小结节（SPN）良恶性判断中的应用。方法收集2000例经病理证实的SPN临床表现及影像学特征,采用SPSS13.0统计学软件将各观察指标进行多因素回归分析,与SPN病理相关指标作为SVM分析参数,对1500例进行训练,另对500例进行预测,对照病理结果分析。结果与病理对照,500例SVM中良性正确预测238（98.5%）例,错误预测4（1.5%）例;恶性正确预测250（97%）例,错误预测8（3%）例。结论 SVM能有效地对SPN良恶性进行较精确的预测,对医生正确诊断有很好的帮助。     

Auditory motion direction encoding in auditory cortex and high-level visual cortex

The aim of this functional magnetic resonance imaging (fMRI) study was to identify human brain areas that are sensitive to the direction of auditory motion. Such directional sensitivity was assessed in a hypothesis-free manner by analyzing fMRI response patterns across the entire brain volume using a spherical-searchlight approach. In addition, we assessed directional sensitivity in three predefined brain areas that have been associated with auditory motion perception in previous neuroimaging studies. These were the primary auditory cortex, the planum temporale and the visual motion complex (hMT/V5+). Our whole-brain analysis revealed that the direction of sound-source movement could be decoded from fMRI response patterns in the right auditory cortex and in a high-level visual area located in the right lateral occipital cortex. Our region-of-interest-based analysis showed that the decoding of the direction of auditory motion was most reliable with activation patterns of the left and right planum temporale. Auditory motion direction could not be decoded from activation patterns in hMT/V5+. These findings provide further evidence for the planum temporale playing a central role in supporting auditory motion perception. In addition, our findings suggest a cross-modal transfer of directional information to high-level visual cortex in healthy humans.     

Active Relearning for Robust Supervised Training of Emphysema Patterns

Radiologists are adept at recognizing the character and extent of lung parenchymal abnormalities in computed tomography (CT) scans. However, the inconsistent differential diagnosis due to subjective aggregation necessitates the exploration of automated classification based on supervised or unsupervised learning. The robustness of supervised learning depends on the training samples. Towards optimizing emphysema classification, we introduce a physician-in-the-loop feedback approach to minimize ambiguity in the selected training samples. An experienced thoracic radiologist selected 412 regions of interest (ROIs) across 15 datasets to represent 124, 129, 139 and 20 training samples of mild, moderate, severe emphysema and normal appearance, respectively. Using multi-view (multiple metrics to capture complementary features) inductive learning, an ensemble of seven un-optimized support vector models (SVM) each based on a specific metric was constructed in less than 6 s. The training samples were classified using seven SVM models and consensus labels were created using majority voting. In the active relearning phase, the ensemble-expert label conflicts were resolved by the expert. The efficacy and generality of active relearning feedback was assessed in the optimized parameter space of six general purpose classifiers across the seven dissimilarity metrics. The proposed just-in-time active relearning feedback with un-optimized SVMs yielded 15 % increase in classification accuracy and 25 % reduction in the number of support vectors. The average improvement in accuracy of six classifiers in their optimized parameter space was 21 %. The proposed cooperative feedback method enhances the quality of training samples used to construct automated classification of emphysematous CT scans. Such an approach could lead to substantial improvement in quantification of emphysema.     

Identifying splicing sites in eukaryotic RNA: support vector machine approach

We introduce a new method for splicing sites prediction based on the theory of support vector machines (SVM). The SVM represents a new approach to supervised pattern classification and has been successfully applied to a wide range of pattern recognition problems. In the process of splicing sites prediction, the statistical information of RNA secondary structure in the vicinity of splice sites, e.g. donor and acceptor sites, is introduced in order to compare recognition ratio of true positive and true negative. From the results of comparison, addition of structural information has brought no significant benefit for the recognition of splice sites and had even lowered the rate of recognition. Our results suggest that, through three cross validation, the SVM method can achieve a good performance for splice sites identification.     

基于改进蝙蝠算法的工业控制系统入侵检测

针对蝙蝠算法（BA）易陷入局部极小的缺点,提出了两点改进：（1）在蝙蝠位置更新时考虑了当前局部最优解分布对算法的影响;（2）将差分进化算法（DE）中的变异操作迁移到蝙蝠算法中,采用随机性变异的方式增加了种群多样性,提升了算法局部搜索能力,并通过典型测试函数验证了本文算法的优越性。将该算法用于工业控制系统（ICS）入侵检测中支持向量机（SVM）分类器的参数优化,使用工控入侵检测标准数据集进行仿真研究。结果表明,与DE、粒子群算法（PSO）和遗传算法（GA）等优化算法相比,其优化的SVM入侵检测模型在检测率、漏报率和误报率等指标上都有显著提升。     

Improving condition severity classification with an efficient active learning based framework

Classification of condition severity can be useful for discriminating among sets of conditions or phenotypes, for example when prioritizing patient care or for other healthcare purposes. Electronic Health Records (EHRs) represent a rich source of labeled information that can be harnessed for severity classification. The labeling of EHRs is expensive and in many cases requires employing professionals with high level of expertise. In this study, we demonstrate the use of Active Learning (AL) techniques to decrease expert labeling efforts. We employ three AL methods and demonstrate their ability to reduce labeling efforts while effectively discriminating condition severity. We incorporate three AL methods into a new framework based on the original CAESAR (Classification Approach for Extracting Severity Automatically from Electronic Health Records) framework to create the Active Learning Enhancement framework (CAESAR-ALE). We applied CAESAR-ALE to a dataset containing 516 conditions of varying severity levels that were manually labeled by seven experts. Our dataset, called the “CAESAR dataset,” was created from the medical records of 1.9 million patients treated at Columbia University Medical Center (CUMC). All three AL methods decreased labelers’ efforts compared to the learning methods applied by the original CAESER framework in which the classifier was trained on the entire set of conditions; depending on the AL strategy used in the current study, the reduction ranged from 48% to 64% that can result in significant savings, both in time and money. As for the PPV (precision) measure, CAESAR-ALE achieved more than 13% absolute improvement in the predictive capabilities of the framework when classifying conditions as severe. These results demonstrate the potential of AL methods to decrease the labeling efforts of medical experts, while increasing accuracy given the same (or even a smaller) number of acquired conditions. We also demonstrated that the methods included in the CAESAR-ALE framework (Exploitation and Combination_XA) are more robust to the use of human labelers with different levels of professional expertise.