Ground target detection, classification and sensor fusion in distributed fiber seismic sensor network - art. no. 683015

This paper describes the ground target detection, classification and sensor fusion problems in distributed fiber seismic sensor network. Compared with conventional piezoelectric seismic sensor used in UGS, fiber optic sensor has advantages of high sensitivity and resistance to electromagnetic disturbance. We have developed a fiber seismic sensor network for target detection and classification. However, ground target recognition based on seismic sensor is a very challenging problem because of the non-stationary characteristic of seismic signal and complicated real life application environment. To solve these difficulties, we study robust feature extraction and classification algorithms adapted to fiber sensor network. An united multi-feature (UMF) method is used. An adaptive threshold detection algorithm is proposed to minimize the false alarm rate. Three kinds of targets comprise personnel, wheeled vehicle and tracked vehicle are concerned in the system. The classification simulation result shows that the SVM classifier outperforms the GMM and BPNN. The sensor fusion method based on D-S evidence theory is discussed to fully utilize information of fiber sensor array and improve overall performance of the system. A field experiment is organized to test the performance of fiber sensor network and gather real signal of targets for classification testing.

应用SVM预测杜鹃属（Rhododendron L.）在中国的潜在分布中心

杜鹃属(Rhododendron L.)是中国种子植物中最大的属，其现代分布和分化中心是我国西南部的横断山区和东喜马拉雅地区。我国西部、西南部的云南、四川、西藏等地共有杜鹃达450种，仅特有种就有约300种。对杜鹃属分布的深入研究是横断山区生物多样性保护不可缺少的重要部分。 由于物种分布与环境因子之间存在着紧密的联系，利用环境因子作为预测物种分布模型的变量是当前最普遍的建模思路。但是绝大多数物种分布预测模型都遇到了难以解决的“高维小样本”问题――模型在标本数据不足时无法给出合理的预测，或者模型无法处理大量的环境变量。机器学习领域的理论和实践已经证明，基于结构风险最小化原理的支持向量机(Support Vector Machine, SVM)算法非常适合“高维小样本”的分类问题。为了探索其应用在物种分布预测问题上的可能性，本文创新性的实现了基于SVM算法的物种分布预测系统。然后，本文以30个杜鹃属(Rhododendron L.)物种为检验对象，利用其标本数据和11个1km的栅格环境变量图层作为模型变量，预测其在中国的潜在分布区。本文通过全面的模型评估——专家评估，ROC (Receiver Operator Characteristic)曲线和曲线下方面积AUC (Area Under the Curve)——来比较模型的性能。试验结果表明，我们所实现的以SVM为核心的物种分布预测系统无论在计算速度还是预测效果上都远远优于当前广泛使用的GARP (Genetic Algorithm for Rule-Set Prediction)预测系统。 之后，本文进一步探讨了SVM预测系统预测效果与环境变量维数和标本点个数的关系。试验结果表明，对于只有少量标本点的物种SVM的预测结果仍然具有相当的合理性。由此可见， SVM预测系统很好的解决了以前众多模型无法克服的稀有种和标本点稀少的物种的潜在分布区模拟问题。同时本文发现大的环境维数（高维）对于物种潜在分布区的预测有着决定性的作用，因此模型处理高维问题的能力显得至关重要。 最后，我们使用中国所有可获取的杜鹃属标本数据，以及83个1km的栅格环境变量图层，对400种杜鹃属物种的潜在分布区进行预测。根据预测出来的物种潜在分布区，我们得到了中国杜鹃属物种潜在多样性分布格局，特有物种潜在多样性分布格局，濒危杜物种潜在的分布格局，各亚属物种潜在分布格局，以及不同生活型物种潜在多样性分布格局。这些分布区图不仅可以对杜鹃属起源研究提供分析验证的条件，还能为其引种、保护和新种的搜寻提供有利的空间依据。

Study on Closed-set Speaker Identification Based on Biomimetic Pattern Recognition

In this paper, a new classifier of speaker identification has been proposed, which is based on Biomimetic pattern recognition (BPR). Distinguished from traditional speaker recognition methods, such as DWT, HMM, GMM, SVM and so on, the proposed classifier is constructed by some finite sub-space which is reasonable covering of the points in high dimensional space according to distributing characteristic of speech feature points. It has been used in the system of speaker identification. Experiment results show that better effect could be obtained especially with lesser samples. Furthermore, the proposed classifier employs a much simpler modeling structure as compared to the GMM. In addition, the basic idea "cognition" of Biomimetic pattern recognition (BPR) results in no requirement of retraining the old system for enrolling new speakers.

The image coding scheme based on neural network and SVM

This paper applies data coding thought, which based on the virtual information source modeling put forward by the author, to propose the image coding (compression) scheme based on neural network and SVM. This scheme is composed by "the image coding (compression) scheme based oil SVM" embedded "the lossless data compression scheme based oil neural network". The experiments show that the scheme has high compression ratio under the slightly damages condition, partly solve the contradiction which 'high fidelity' and 'high compression ratio' cannot unify in image coding system.

Lossless data compression scheme based on neural network and SVM

First, the compression-awaited data are regarded Lis character strings which are produced by virtual information source mapping M. then the model of the virtual information source M is established by neural network and SVM. Last we construct a lossless data compression (coding) scheme based oil neural network and SVM with the model, an integer function and a SVM discriminant. The scheme differs from the old entropy coding (compressions) inwardly, and it can compress some data compressed by the old entropy coding.

Cancer classification based on direction-basis-function neural networks

Automatic molecular classification of cancer based on DNA microarray has many advantages over conventional classification based on morphological appearance of the tumor. Using artificial neural networks is a general approach for automatic classification. In this paper, Direction-Basis-Function neuron and Priority-Ordered algorithm are applied to neural networks. And the leukemia gene expression dataset is used as an example to testify the classifier. The result of our method is compared to that of SVM. It shows that our method makes a better performance than SVM.

Comparing the Performance of Biomimetic Pattern Recognition with W8 and SVM on Prediction of Horizontal Gene Transfers in Bacteria Genomes

National Natural Science Foundation of China 60753001

基于模板匹配和SVM的草图符号自适应识别方法

草图符号的自适应学习中，不同用户的训练样本数量可能不同。保持在不同样本数量下良好的学习效果成为需要解决的一个重要问题．提出一种自适应的草图符号识别方法，该方法采用与训练样本个数相关的分类器组合策略将模板匹配方法和SVM统计分类方法进行了高效组合．它通过利用支持小样本学习的模板匹配方法和支持大量样本学习的SVM方法，并同时利用草图符号中的在线信息和离线信息，实现了不同样本个数下自适应的符号学习和识别．基于该方法，文中设计并实现了支持自适应识别的草图符号组件．最后，利用扩展的PIBGToolkit开发出原型系统IdeaNote．评估表明，该方法可以在24类草图符号分别使用1到20个训练样本时具有较高的识别正确率和较好的时间性能．

人脸检测的一种混合方法研究

人脸检测作为自动人脸识别系统的第一个环节具有非常重要的作用,为了解决目前大部分人脸检测方法存在的分类器训练困难和检测计算量大等问题,提出了一种人脸检测的混合方法。该方法由两级分类器组成,第一级为粗分类器主要过滤大部分非人脸区域,第二级为核心分类器,在由第一级粗分类的基础上利用非线性SVM算法进行人脸检测。在CMU数据库上的实验结果表明,该方法具有较高的人脸检测率,检测速度得到大幅提高。

Sensitivity map of laser tweezers Raman spectroscopy for single-cell analysis of colorectal cancer

Raman spectroscopy on single, living epithelial cells captured in a laser trap is shown to have diagnostic power over colorectal cancer. This new single-cell technology comprises three major components: primary culture processing of human tissue samples to produce single-cell suspensions, Raman detection on singly trapped cells, and diagnoses of the cells by artificial neural network classifications. it is compared with DNA flow cytometry for similarities and differences. Its advantages over tissue Raman spectroscopy are also discussed. In the actual construction of a diagnostic model for colorectal cancer, real patient data were taken to generate a training set of 320 Raman spectra and, a test set of 80. By incorporating outlier corrections to a conventional binary neural classifier, our network accomplished significantly better predictions than logistic regressions, with sensitivity improved from 77.5% to 86.3% and specificity improved from 81.3% to 86.3% for the training set and moderate improvements for the test set. Most important, the network approach enables a sensitivity map analysis to quantitate the relevance of each Raman band to the normal-to-cancer transform at the cell level. Our technique has direct clinic applications for diagnosing cancers and basic science potential in the study of cell dynamics of carcinogenesis. (C) 2007 Society of Photo-Optical Instrumentation Engineers.

Sensitivity map of laser tweezers Raman spectroscopy for single-cell analysis of colorectal cancer

Raman spectroscopy on single, living epithelial cells captured in a laser trap is shown to have diagnostic power over colorectal cancer. This new single-cell technology comprises three major components: primary culture processing of human tissue samples to produce single-cell suspensions, Raman detection on singly trapped cells, and diagnoses of the cells by artificial neural network classifications. it is compared with DNA flow cytometry for similarities and differences. Its advantages over tissue Raman spectroscopy are also discussed. In the actual construction of a diagnostic model for colorectal cancer, real patient data were taken to generate a training set of 320 Raman spectra and, a test set of 80. By incorporating outlier corrections to a conventional binary neural classifier, our network accomplished significantly better predictions than logistic regressions, with sensitivity improved from 77.5% to 86.3% and specificity improved from 81.3% to 86.3% for the training set and moderate improvements for the test set. Most important, the network approach enables a sensitivity map analysis to quantitate the relevance of each Raman band to the normal-to-cancer transform at the cell level. Our technique has direct clinic applications for diagnosing cancers and basic science potential in the study of cell dynamics of carcinogenesis. (C) 2007 Society of Photo-Optical Instrumentation Engineers.

Mandarin speech emotion recognition based on high dimensional geometry theory

In this paper, a novel approach for mandarin speech emotion recognition, that is mandarin speech emotion recognition based on high dimensional geometry theory, is proposed. The human emotions are classified into 6 archetypal classes: fear, anger, happiness, sadness, surprise and disgust. According to the characteristics of these emotional speech signals, the amplitude, pitch frequency and formant are used as the feature parameters for speech emotion recognition. The new method called high dimensional geometry theory is applied for recognition. Compared with traditional GSVM model, the new method has some advantages. It is noted that this method has significant values for researches and applications henceforth.