Comparison of pattern recognition methods in classifying high-resolution BOLD signals obtained at high magnetic field in monkeys

Pattern recognition methods have shown that functional magnetic resonance imaging (fMRI) data can reveal significant information about brain activity. For example, in the debate of how object categories are represented in the brain, multivariate analysis has been used to provide evidence of a distributed encoding scheme [Science 293:5539 (2001) 2425–2430]. Many follow-up studies have employed different methods to analyze human fMRI data with varying degrees of success [Nature reviews 7:7 (2006) 523–534]. In this study, we compare four popular pattern recognition methods: correlation analysis, support-vector machines (SVM), linear discriminant analysis (LDA) and Gaussian naïve Bayes (GNB), using data collected at high field (7 Tesla) with higher resolution than usual fMRI studies. We investigate prediction performance on single trials and for averages across varying numbers of stimulus presentations. The performance of the various algorithms depends on the nature of the brain activity being categorized: for several tasks, many of the methods work well, whereas for others, no method performs above chance level. An important factor in overall classification performance is careful preprocessing of the data, including dimensionality reduction, voxel selection and outlier elimination.     

Chemometrics and its applications to x‐ray spectrometry

Recent developments in curve fitting, multivariate calibration, and pattern recognition in chemometrics, and their application to x‐ray spectrometry, are reviewed. Relatively innovated algorithms, namely genetic algorithms, neural networks and support vector machines, are discussed. Together with the three algorithms, the performances of different algorithms are compared briefly, which mainly includes principal component analysis, partial least‐squares regression, factor analysis, cluster analysis, nearest neighbor methods, linear discriminant analysis, linear learning machine, and soft independent modeling of class analogy. In general, the chemometrics methods are superior to the conventional methods, such as Fourier transform and Marquardt–Levenberg algorithms, to a certain extent. Copyright © 2006 John Wiley & Sons, Ltd.     

酒香型光谱分析和模式识别计算分析

白酒是一个复杂的混合物体系,它含有大量的微量成分,这些微量成分直接决定了白酒的品质、口感和香型。为实现对白酒香型的快速鉴别,可采集不同香型白酒的红外光谱图,并将其作为模式分类方法的输入模式,建立白酒香型鉴别模型。首次全面系统地介绍了白酒香型模式识别算法,这些算法包括统计分类器(线性判别函数、二次判别函数、正则判别分析、K近邻算法)、原型学习算法(学习矢量量化)、支持向量机和AdaBoost算法。实验结果表明,基于红外光谱的白酒香型检测模式识别算法达到了很高的分类准确率、识别率和拒绝率,显示出了很好的性能。     

Classifier ensembles for fMRI data analysis: an experiment

Functional magnetic resonance imaging (fMRI) is becoming a forefront brain–computer interface tool. To decipher brain patterns, fast, accurate and reliable classifier methods are needed. The support vector machine (SVM) classifier has been traditionally used. Here we argue that state-of-the-art methods from pattern recognition and machine learning, such as classifier ensembles, offer more accurate classification. This study compares 18 classification methods on a publicly available real data set due to Haxby et al. [Science 293 (2001) 2425–2430]. The data comes from a single-subject experiment, organized in 10 runs where eight classes of stimuli were presented in each run. The comparisons were carried out on voxel subsets of different sizes, selected through seven popular voxel selection methods. We found that, while SVM was robust, accurate and scalable, some classifier ensemble methods demonstrated significantly better performance. The best classifiers were found to be the random subspace ensemble of SVM classifiers, rotation forest and ensembles with random linear and random spherical oracle.     

A survey on HHL algorithm: From theory to application in quantum machine learning

The Harrow-Hassidim-Lloyd (HHL) algorithm is a method to solve the quantum linear system of equations that may be found at the core of various scientific applications and quantum machine learning models including the linear regression, support vector machines and recommender systems etc. After reviewing the necessary background on elementary quantum algorithms, we provide detailed account of how HHL is exploited in different quantum machine learning (QML) models, and how it provides the desired quantum speedup in all these models. At the end, we briefly discuss some of the remaining challenges ahead for HHL-based QML models and related methods.     

Variational quantum support vector machine based on Hadamard test

Classical machine learning algorithms seem to be totally incapable of processing tremendous amounts of data, while quantum machine learning algorithms could deal with big data with ease and provide exponential acceleration over classical counterparts. Meanwhile, variational quantum algorithms are widely proposed to solve relevant computational problems on noisy, intermediate-scale quantum devices. In this paper, we apply variational quantum algorithms to quantum support vector machines and demonstrate a proof-of-principle numerical experiment of this algorithm. In addition, in the classification stage, fewer qubits, shorter circuit depth, and simpler measurement requirements show its superiority over the former algorithms.     

A new type SVM-projected SVM

Support vector machine (SVM), developed by Vapnik et al., is a new and promising technique for classification and regression and has been proved to be competitive with the best available learning machines in many applications. However, the classification speed of SVM is substantially slower than that of other techniques with similar generalization ability. A new type SVM named projected SVM (PSVM), which is a combination of feature vector selection (FVS) method and linear SVM (LSVM), is proposed in present paper. In PSVM, the FVS method is first used to select a relevant subset (feature vectors, FVs) from the training data, and then both the training data and the test data are projected into the subspace constructed by FVs, and finally linear SVM(LSVM) is applied to classify the projected data. The time required by PSVM to calculate the class of new samples is proportional to the count of FVs. In most cases, the count of FVs is smaller than that of support vectors (SVs), and therefore PSVM is faster than SVM in running. Compared with other speeding-up techniques of SVM, PSVM is proved to possess not only speeding-up ability but also de-noising ability for high-noised data, and is found to be of potential use in mechanical fault pattern recognition.     

A new type SVM—projected SVM

Support vector machine (SVM), developed by Vapnik et al., is a new and promising technique for classification and regression and has been proved to be competitive with the best available learning machines in many applications. However, the classification speed of SVM is substantially slower than that of other techniques with similar generalization ability. A new type SVM named projected SVM (PSVM), which is a combination of feature, vector selection (FVS) method and linear SVM (LSVM), is proposed in present paper. In PSVM, the FVS method is first used to select a relevant subset (feature vectors, FVs) from the training data, and then both the training data and the test data are projected into the subspace constructed by FVs, and finally linear SVM (LSVM) is applied to classify the projected data. The time required by PSVM to calculate the class of new samples is proportional to the count of FVs. In most cases, the count of FVs is smaller than that of support vectors (SVs), and therefore PSVM is faster than SVM in running. Compared with other speeding-up techniques of SVM, PSVM is proved to possess not only speeding-up ability but also de-noising ability for high-noised data, and is found to be of potential use in mechanical fault pattern recognition.     

A new type SVM—projected SVM

Support vector machine (SVM), developed by Vapnik et al., is a new and promising technique for classification and regression and has been proved to be competitive with the best available learning machines in many applications. However, the classification speed of SVM is substantially slower than that of other techniques with similar generalization ability. A new type SVM named projected SVM (PSVM), which is a combination of feature, vector selection (FVS) method and linear SVM (LSVM), is proposed in present paper. In PSVM, the FVS method is first used to select a relevant subset (feature vectors, FVs) from the training data, and then both the training data and the test data are projected into the subspace constructed by FVs, and finally linear SVM (LSVM) is applied to classify the projected data. The time required by PSVM to calculate the class of new samples is proportional to the count of FVs. In most cases, the count of FVs is smaller than that of support vectors (SVs), and therefore PSVM is faster than SVM in running. Compared with other speeding-up techniques of SVM, PSVM is proved to possess not only speeding-up ability but also de-noising ability for high-noised data, and is found to be of potential use in mechanical fault pattern recognition.

     

数据驱动模型的血液物种光谱检测技术

介绍一种基于光谱检测和数据驱动模型的非接触式血液物种识别技术。选取了4个物种(猴144,大鼠203,狗133,人169)共计649个血样作为原始样本。超连续谱激光光源的波长范围是450～2 400 nm。分别采集抗凝管盛装血液样本的后向散射可见光谱(294～1 160 nm)和十个不同空间位点的前向散射近红外光谱(1 021～1 757 nm),将十一条光谱数据顺序连接为一维数据作为每个样本的原始数据。利用主成分分析法对数据集进行特征信息提取,保留原始差异信息量的99.99%,同时将数据量压缩为原始数据量的1.5%,提高分类识别的运算效率。对不同数量的训练集和验证集进行训练预测实验表明,十折交叉验证的识别误差率随着样本数量的增加而降低,样本库规模的增大可以提高识别的精确度。由于数据驱动模型是基于机器学习算法的数据流处理模型,因而可以采用多种不同的分类算法实现。通过比较人工神经网络、支持向量机、偏最小二乘回归、多元线性回归、随机森林和朴素贝叶斯的识别效果可以发现,不同算法的识别效果具有类别差异性,即各个算法的正确识别率排序在不同的物种中是有差异的。因而实际应用中,在选择数据驱动模型时,除了需要考虑算法的整体识别率之外,当对部分类别的识别效果有额外要求时,还应该考虑算法本身的类别差异性。     

An Overview of Infrared Spectroscopy Based on Continuous Wavelet Transform Combined with Machine Learning Algorithms: Application to Chinese Medicines,Plant Classification,and Cancer Diagnosis

Abstract

Infrared spectroscopy has been a workhorse technique for materials analysis and can result in positively identifying many different types of material. In recent years there have been reports using wavelet analysis and machine learning algorithms to extract features of Fourier transform infrared spectrometry (FTIR). The machine learning algorithms contain back-propagation neural network (BPNN), radial basis function neural network (RBFNN), and support vector machine (SVM). This article reviews the important advances in FTIR analysis employing a continuous wavelet transform (CWT) and machine learning algorithms, especially in the applications of the method for Chinese medicine identification, plant classification, and cancer diagnosis.     

Brain Inspired Cortical Coding Method for Fast Clustering and Codebook Generation

Highlights What are the main findings?

• A cortical coding method is developed inspired by the network formation in the brain, where the information entropy is maximized while dissipated energy is minimized.
• The execution time in the cortical coding model is far superior, seconds versus minutes or hours, compared to those of the frequently used current algorithms, while retaining comparable distortion rate.

What is the implication of the main finding?

• The significant attribute of the methodology is its generalization performance, i.e., learning rather than memorizing data.
• Although only vector quantization property was demonstrated herein, the cortical coding algorithm has a real potential in a wide variety of real-time machine learning implementations such as , temporal clustering, data compression, audio and video encoding, anomaly detection, and recognition, to list a few.

AbstractA major archetype of artificial intelligence is developing algorithms facilitating temporal efficiency and accuracy while boosting the generalization performance. Even with the latest developments in machine learning, a key limitation has been the inefficient feature extraction from the initial data, which is essential in performance optimization. Here, we introduce a feature extraction method inspired by energy–entropy relations of sensory cortical networks in the brain. Dubbed the brain-inspired cortex, the algorithm provides convergence to orthogonal features from streaming signals with superior computational efficiency while processing data in a compressed form. We demonstrate the performance of the new algorithm using artificially created complex data by comparing it with the commonly used traditional clustering algorithms, such as Birch, GMM, and K-means. While the data processing time is significantly reduced—seconds versus hours—encoding distortions remain essentially the same in the new algorithm, providing a basis for better generalization. Although we show herein the superior performance of the cortical coding model in clustering and vector quantization, it also provides potent implementation opportunities for machine learning fundamental components, such as reasoning, anomaly detection and classification in large scope applications, e.g., finance, cybersecurity, and healthcare.     

Real-time functional magnetic resonance imaging: methods and applications

Functional magnetic resonance imaging (fMRI) has been limited by time-consuming data analysis and a low signal-to-noise ratio, impeding online analysis. Recent advances in acquisition techniques, computational power and algorithms increased the sensitivity and speed of fMRI significantly, making real-time analysis and display of fMRI data feasible. So far, most reports have focused on the technical aspects of real-time fMRI (rtfMRI). Here, we provide an overview of the different major areas of applications that became possible with rtfMRI: online analysis of single-subject data provides immediate quality assurance and functional localizers guiding the main fMRI experiment or surgical interventions. In teaching, rtfMRI naturally combines all essential parts of a neuroimaging experiment, such as experimental design, data acquisition and analysis, while adding a high level of interactivity. Thus, the learning of essential knowledge required to conduct functional imaging experiments is facilitated. rtfMRI allows for brain-computer interfaces (BCI) with a high spatial and temporal resolution and whole-brain coverage. Recent studies have shown that such BCI can be used to provide online feedback of the blood-oxygen-level-dependent signal and to learn the self-regulation of local brain activity. Preliminary evidence suggests that this local self-regulation can be used as a new paradigm in cognitive neuroscience to study brain plasticity and the functional relevance of brain areas, even being potentially applicable for psychophysiological treatment.     

近红外化学模式识别方法及应用研究

近红外模式识别技术是现代近红外光谱分析技术的一个重要方面。文章较系统地介绍了近红外模式识别中常用的化学模式识别方法和这一领域内的最新进展,涉及到聚类分析、判别分析、特征投影显示3个方面多种方法的基本原理,以及近年来出现的支持向量机(SVM)、气泡凝聚算法(BA)、焦点本征函数(FEF)等新方法的基本思想。综述了近几年近红外模式识别技术在农业、医药、食品分析、石油等领域的具体应用。     

A kernel machine-based fMRI physiological noise removal method

Functional magnetic resonance imaging (fMRI) technique with blood oxygenation level dependent (BOLD) contrast is a powerful tool for noninvasive mapping of brain function under task and resting states. The removal of cardiac- and respiration-induced physiological noise in fMRI data has been a significant challenge as fMRI studies seek to achieve higher spatial resolutions and characterize more subtle neuronal changes. The low temporal sampling rate of most multi-slice fMRI experiments often causes aliasing of physiological noise into the frequency range of BOLD activation signal. In addition, changes of heartbeat and respiration patterns also generate physiological fluctuations that have similar frequencies with BOLD activation. Most existing physiological noise-removal methods either place restrictive limitations on image acquisition or utilize filtering or regression based post-processing algorithms, which cannot distinguish the frequency-overlapping BOLD activation and the physiological noise. In this work, we address the challenge of physiological noise removal via the kernel machine technique, where a nonlinear kernel machine technique, kernel principal component analysis, is used with a specifically identified kernel function to differentiate BOLD signal from the physiological noise of the frequency. The proposed method was evaluated in human fMRI data acquired from multiple task-related and resting state fMRI experiments. A comparison study was also performed with an existing adaptive filtering method. The results indicate that the proposed method can effectively identify and reduce the physiological noise in fMRI data. The comparison study shows that the proposed method can provide comparable or better noise removal performance than the adaptive filtering approach.     

Cortex-based independent component analysis of fMRI time series

The cerebral cortex is the main target of analysis in many functional magnetic resonance imaging (fMRI) studies. Since only about 20% of the voxels of a typical fMRI data set lie within the cortex, statistical analysis can be restricted to the subset of the voxels obtained after cortex segmentation. While such restriction does not influence conventional univariate statistical tests, it may have a substantial effect on the performance of multivariate methods.

Here, we describe a novel approach for data-driven analysis of single-subject fMRI time series that combines techniques for the segmentation and reconstruction of the cortical surface of the brain and the spatial independent component analysis (sICA) of the functional time courses (TCs). We use the mesh of the white matter/gray matter boundary, automatically reconstructed from high-spatial-resolution anatomical MR images, to limit the sICA decomposition of a coregistered functional time series to those voxels which are within a specified region with respect to the cortical sheet (cortex-based ICA, or cbICA). We illustrate our analysis method in the context of fMRI blocked and event-related experimental designs and in an fMRI experiment with perceptually ambiguous stimulation, in which an a priori specification of the stimulation protocol is not possible.

A comparison between cbICA and conventional hypothesis-driven statistical methods shows that cortical surface maps and component TCs blindly obtained with cbICA reliably reflect task-related spatiotemporal activation patterns. Furthermore, the advantages of using cbICA when the specification of a temporal model of the expected hemodynamic response is not straightforward are illustrated and discussed. A comparison between cbICA and anatomically unconstrained ICA reveals that — beside reducing computational demand — the cortex-based approach improves the fitting of the ICA model in the gray matter voxels, the separation of cortical components and the estimation of their TCs, particularly in the case of fMRI data sets with a complex spatiotemporal statistical structure.     

Surface-based functional magnetic resonance imaging analysis of partial brain echo planar imaging data at 1.5 T

Surface-based functional magnetic resonance imaging (fMRI) analysis is more sensitive and accurate than volume-based analysis for detecting neural activation. However, these advantages are less important in practical fMRI experiments with commonly used 1.5-T magnetic resonance devices because of the resolution gap between the echo planar imaging data and the cortical surface models. We expected high-resolution segmented partial brain echo planar imaging (EPI) data to overcome this problem, and the activation patterns of the high-resolution data could be different from the low-resolution data. For the practical applications of surface-based fMRI analysis using segmented EPI techniques, the effects of some important factors (e.g., activation patterns, registration and local distortions) should be intensively evaluated because the results of surface-based fMRI analyses could be influenced by them. In this study, we demonstrated the difference between activations detected from low-resolution EPI data, which were covering whole brain, and high-resolution segmented EPI data covering partial brain by volume- and surface-based analysis methods. First, we compared the activation maps of low- and high-resolution EPI datasets detected by volume- and surface-based analyses, with the spatial patterns of activation clusters, and analyzed the distributions of activations in occipital lobes. We also analyzed the high-resolution EPI data covering motor areas and fusiform gyri of human brain, and presented the differences of activations detected by volume- and surface-based methods.     

Fixed-point algorithms for constrained ICA and their applications in fMRI data analysis

Constrained independent component analysis (CICA) eliminates the order ambiguity of standard ICA by incorporating prior information into the learning process to sort the components intrinsically. However, the original CICA (OCICA) and its variants depend on a learning rate, which is not easy to be tuned for various applications. To solve this problem, two learning-rate-free CICA algorithms were derived in this paper using the fixed-point learning concept. A complete stability analysis was provided for the proposed methods, which also made a correction to the stability analysis given to OCICA. Variations for adding constraints either to the components or to the associated time courses were derived too. Using synthetic data, the proposed methods yielded a better stability and a better source separation quality in terms of higher signal-to-noise-ratio and smaller performance index than OCICA. For the artificially generated brain activations, the new CICAs demonstrated a better sensitivity/specificity performance than standard univariate general linear model (GLM) and standard ICA. Original CICA showed a similar sensitivity/specificity gain but failed to converge for several times. Using functional magnetic resonance imaging (fMRI) data acquired with a well-characterized sensorimotor task, the proposed CICAs yielded better sensitivity than OCICA, standard ICA and GLM in all the target functional regions in terms of either higher t values or larger suprathreshold cluster extensions using the same significance threshold. In addition, they were more stable than OCICA and standard ICA for analyzing the sensorimotor fMRI data.     

Spatially aggregated multiclass pattern classification in functional MRI using optimally selected functional brain areas

In previous works, boosting aggregation of classifier outputs from discrete brain areas has been demonstrated to reduce dimensionality and improve the robustness and accuracy of functional magnetic resonance imaging (fMRI) classification. However, dimensionality reduction and classification of mixed activation patterns of multiple classes remain challenging. In the present study, the goals were (a) to reduce dimensionality by combining feature reduction at the voxel level and backward elimination of optimally aggregated classifiers at the region level, (b) to compare region selection for spatially aggregated classification using boosting and partial least squares regression methods and (c) to resolve mixed activation patterns using probabilistic prediction of individual tasks. Brain activation maps from interleaved visual, motor, auditory and cognitive tasks were segmented into 144 functional regions. Feature selection reduced the number of feature voxels by more than 50%, leaving 95 regions. The two aggregation approaches further reduced the number of regions to 30, resulting in more than 75% reduction of classification time and misclassification rates of less than 3%. Boosting and partial least squares (PLS) were compared to select the most discriminative and the most task correlated regions, respectively. Successful task prediction in mixed activation patterns was feasible within the first block of task activation in real-time fMRI experiments. This methodology is suitable for sparsifying activation patterns in real-time fMRI and for neurofeedback from distributed networks of brain activation.     

基于流形学习的极端学习机及其在人脸识别中的应用

极端学习机以其快速高效和良好的泛化能力在模式识别领域得到了广泛应用,然而现有的ELM及其改进算法并没有充分考虑到数据维数对ELM分类性能和泛化能力的影响,当数据维数过高时包含的冗余属性及噪音点势必降低ELM的泛化能力,针对这一问题本文提出一种基于流形学习的极端学习机,该算法结合维数约减技术有效消除数据冗余属性及噪声对ELM分类性能的影响,为验证所提方法的有效性,实验使用普遍应用的图像数据,实验结果表明本文所提算法能够显著提高ELM的泛化性能。