Acquired Predator Recognition by Fathead Minnows: Influence of Habitat Characteristics on Survival

In this study we conditioned fathead minnows (Pimephales promelas) to recognize the odor of a perch (Perca flavescens) by exposing them to perch odor coupled with minnow alarm cue. We then staged encounters between the predator and prey in order to assess whether the predator odor training had any effect on survival of the prey. We tested for a survival effect in the presence and absence of shelter. Our results indicate that fish trained with alarm signals to recognize predators gained a survival benefit during staged encounters with a predator and that habitat characteristics influenced the survival of conditioned fish.     

基于多特征融合的运动物体识别方法研究

为了实现运动目标的实时检测,本文基于多特征融合,提出了一种运动物体分级识别方法.首先通过对运动目标的分割,分析得到各个物体的形状矩特征、面积大小及运动速度.对上述特征,采用支持向量机方法对其矩特征进行快速的一级分类,然后对一级分类结果及各物体的面积、速度等信源根据其对分类的重要程度,采用模糊积分技术进行多特征融合分类.实验表明,本方法具有较强的学习能力及较高的识别精度,可有效地应用于道路监控等系统.     

A recognition method of vibration parameter image based on improved immune negative selection algorithm for rotating machinery

To overcome the limitations of traditional monitoring methods, based on vibration parameter image of rotating machinery, this paper presents an abnormality online monitoring method suitable for rotating machinery using the negative selection mechanism of biology immune system. This method uses techniques of biology clone and learning mechanism to improve the negative selection algorithm to generate detectors possessing different monitoring radius, covers the abnormality space effectively, and avoids such problems as the low efficiency of generating detectors, etc. The result of an example applying the presented monitoring method shows that this method can solve the difficulty of obtaining fault samples preferably and extract the turbine state character effectively, it also can detect abnormality by causing various fault of the turbine and obtain the degree of abnormality accurately. The exact monitoring precision of abnormality indicates that this method is feasible and has better on-line quality, accuracy and robustness.     

小波域声呐图像自适应增强

声呐图像受噪声污染严重、对比度低,给后期的定位识别带来不便,而传统的处理方法容易造成边缘模糊.针对这一问题,提出了一种图像自适应增强算法.该算法利用形态小波对声呐图像进行自适应的多分辨率分析,分别增强不同尺度上的信号或细节,通过多通道重构图像的加权实现去噪和对比度提高.仿真结果表明该算法快速有效,对高斯噪声和冲击性噪声都具有较好的鲁棒性,处理后的声呐图像边缘细节信息保留完好,得到了理想的增强效果.     

一种基于步幅长度及频域特征的步态识别方法

步态识别作为一种较新的生物认证技术有其独特优势,它旨在根据人行进过程中的行走步态模式来识别其身份.提出一种基于步幅长度及频域特征的步态识别方法:首先采用背景减除算法实现运动人体检测,并根据步幅长度变化特征进行周期分割.然后提取步幅长度极值结合关键帧的频幅均值构成五维特征向量,最后用标准模式分类器在中科院自动化所提供的CASIA步态数据库中进行实验,在降低了算法复杂度的同时,获得了令人鼓舞的实验结果.     

一种基于图像识别的高性能混沌特性判别算法

利用混沌阵子可以检测强噪声背景下极其微弱的周期信号。该方法应用中的关键问题是混沌特性的判别。提出了一种新的基于图像识别的混沌特性判别方法,该方法需要的存储量小,算法简单易行,尤其适合系统资源受限的场合,比如嵌入式系统。阐述了该混沌特性判别算法的原理,给出了一个基于此方法的完整判别程序流程。计算机仿真结果表明,该方法用于Duffing信号幅值检测系统是有效的。     

Macromolecular recognition by cyclodextrins. Interaction of cyclodextrins with polymethacrylamides bearing hydrophobic amino acid residues

The interaction of cyclodextrins (CDs) with poly(N-methacryloyltryptophan) (pMTrp) and with poly(N-methacryloylphenylalanine) (pMPhe) was investigated as a simple model system of macromolecular recognition of proteins. The association constants (K) for the model compounds, sodium salts of tryptophan and phenylalanine, are not so different (i.e. 43 and 16 M⁻¹ for α-CD, 59 and 69 M⁻¹ for β-CD, and 12 and 3 M⁻¹ for γ-CD, respectively). On the other hand, there is a significant difference in the apparent K values for pMTrp and pMPhe (i.e. the K values for pMPhe are considerably smaller than ca. 10 M⁻¹, whereas those for pMTrp are 30, 83, and 11 M⁻¹ for α-, β-, and γ-CDs, respectively). These observations indicate that a subtle difference in polymer side chains can be critical in macromolecular recognition.     

PATTERN RECOGNITION APLLIED TO STABILITY OF FILLED Ti_2Ni PHASES

Pattern recognition method is used for the investigation of stability,region of filled Ti_2Niphases in multi-dimensional bond-parameter space.The filling of C,N and O atoms intoT_6 octahedra consisting of atoms of earhy-transition elements makes the expansion of thestability region of Ti_2Ni phase,and the relative stability of AI_2Cu and MoSi_2 type com-pounds decreases after the introduction of non-metallic elements such as C,N and O.     

基于逻辑回归模型的木片和树皮的图像识别

为了提高木片生物能的利用率,需要除去木片中的树皮杂质。识别木片和树皮的图像对于实现二者分离具有重要作用。提出一种基于逻辑回归模型来对木片和树皮进行图像识别的算法。算法流程包括计算各种可以描述木片和树皮纹理的参数,利用SAS统计分析出最佳参数,将最佳参数计算所得的样本数据用于SAS LOGISTIC过程得到预测方程,再将预测方程用于逻辑回归模型来实现木片和树皮的图像识别。通过实验可知,最佳参数为灰度方差,该图像识别算法的正确率能达到97.4%。     

基于细胞神经网络和网格特征的碑刻文字识别

碑刻作为文字的载体,具有极其重要的历史价值和艺术价值。但是,因为时间的久远,其拓本大量的噪声对碑刻文字的辨识产生一定的影响。针对这种情况,提出了一种新方法,首先利用细胞神经网络（CNN）技术,去除单个碑刻文字的噪声,然后用网格特征提取方法对其进行识别。本文在MATLAB平台上进行了实例模拟,取得了较好的效果。