加筋板材料辨识的导纳特征表达与冲击声特征提取

以表征物理属性的导纳特征为中间量,提取与加筋板材料属性有关的冲击声特征。先用相关分析方法获得金属加筋板物理属性的导纳特征表达以及导纳特征与冲击声特征之间的联系,间接得到表征声源物理属性的冲击声特征,然后通过支持向量机分类器验证不同特征在金属加筋板材料分类辨识中的性能。结果表明,所得的4组冲击声特征能准确识别出不同的材料,单个特征的识别率与对应材料属性的可分程度有关,理想冲击声声特征比音色特征的平均识别率更高。由此可见,利用导纳特征提取与材料属性相关冲击声特征的方法是有效的,且所提的特征能够很好的反映声源材料属性。     

基于平板冲击声的声源特性表征及自动识别*

以平板结构导纳函数为纽带,建立冲击声信号特征与声源特性之间的关联,获得与声源属性密切相关的特征用于目标分类。针对四边简支矩形被击板,借助信号参数识别算法获得与声源物理属性有关的6维导纳特征,并从冲击声样本中提取80维音色特征,将音色特征和导纳特征做相关性分析,获得与声源物理属性相关的信号特征集。利用BP神经网络进行分类,结果表明,当采用与特定声源物理属性相关的信号特征子集时,分类效果达到同组最优。     

利用冲击声辨识声源材料的特征提取

声源辨识属于环境声识别的范畴,是模式识别的一个重要研究方向。冲击声携带了大量的声源物理信息,因此利用冲击声提取特征进行声源材料辨识是提高声目标识别分类性能的重要途径。对球-板撞击物理模型合成的冲击声连续统,提出使用基函数学习法提取目标特征,同时利用短时傅里叶变换和小波包变换进行特征提取,以此为基础完成被击平板的材料识别。研究结果表明,利用基函数学习法获得的特征,对于冲击声分类的效果明显优于短时傅里叶变换和小波包变换方法,说明利用该方法进行冲击声声源材料辨识的可行性和优势。     

Feature extraction for sound source material recognition with impact sounds

Sound source recognition is a part of environmental sound recognition,which is one of the most important research areas in pattern recognition.Impact sounds carry much physical information associated with the sound sources,which makes impact sound based sound source recognition an important approach to improve recognition performance.In this study,the impact sound continuum synthesized with a ball-plate collision model is used for material recognition of the impacted plates.The basis function learning method and time-frequency representation methods,including the short time Fourier transform and the wavelet packet transform,are applied into classification and the recognition results are compared.The result shows that the features obtained by using the basis function learning perform better for material classification of the impacted plates than that by using the short time Fourier transform and the wavelet packet transform.This demonstrates the high efficiency and superiority of this method in material recognition of sound sources.     

Sound Signal Based Fault Classification System in Motorcycles Using Hybrid Feature Sets and Extreme Learning Machine Classifiers

Vehicles generate dissimilar sound patterns under different working environments. These generated sound patterns signify the condition of the engines, which in turn is used for diagnosing various faults. In this paper, the sound signals produced by motorcycles are analyzed to locate various faults. The important attributes are extracted from the generated sound signals based on time, frequency and wavelet domains which clearly describe the statistical behavior of the signals. Further, various types of faults are classified using the Extreme Learning Machine (ELM) classifier from the extracted features. Moreover, the improved classification performance is obtained by the combination of feature sets in different domains. The simulation results clearly demonstrate that the proposed hybrid feature set together with the ELM classifier gives more promising results with higher classification accuracy when compared with the other conventional methods.     

近岸4种鱼的声散射特征提取及融合实验研究*

为了有效地提取表征鱼类间差异的声散射特征参数,该文通过绳系法实验研究了近岸4种经济鱼类的声散射信号特征提取及融合方法。首先,通过自研双频鱼探仪采集花鲈、许氏平鲉、黑鲷和斑石鲷的个体鱼声散射信号;然后,分别测定200 kHz和450 kHz换能器下鱼体的目标强度,同时提取鱼声散射信号的时频域统计特征;最后,将降维后的时频特征与频差特征融合组成新的特征向量。该文通过实验验证了该方法的有效性,基于组合特征的支持向量机识别准确率达93%。结果表明,鱼的频率响应特性和鱼声散射信号的时频域统计特征能一定程度上反映鱼的固有属性,有效地增加判别依据能显著提高以上4种鱼类的识别准确率。     

基于特征选择的网络入侵检测模型研究

为了有效从收集的恶意数据中选择特征去分析,保障网络系统的安全与稳定,需要进行网络入侵检测模型研究。但目前方法是采用遗传算法找出网络入侵的特征子集,再利用粒子群算法进行进一步选择,找出最优的特征子集,最后利用极限学习机对网络入侵进行分类,但该方法准确性较低。为此,提出一种基于特征选择的网络入侵检测模型研究方法。该方法首先以增强寻优性能为目标对网络入侵检测进行特征选择,结合分析出的特征选择利用特征属性的Fisher比构造出特征子集的评价函数,然后结合计算出的特征子集评价函数进行支持向量机完成对基于特征选择的网络入侵检测模型研究方法。仿真实验表明,利用支持向量机对网络入侵进行检测能有效地提高入侵检测的速度以及入侵检测的准确性。     

Calculation of airborne and impact sound insulation between dwellings

Some years ago a model was described for the calculation of the weighted airborne sound insulation between dwellings. Further work has been done since in order to increase the applicability of this model, including the extension to octave band calculations.Besides airborne sound, impact sound is also of importance. Therefore the calculation model has also been extended to impact sound insulation. These calculations are based largely on the same input data as for airborne sound. A new quantity however is the floor admittance. For homogeneous floors an existing model for the calculation of the admittance could be applied. For typical (Dutch) floor constructions consisting of concrete beams and plates a model for the admittance has been developed, based on admittance measurements in situ.Some examples are given of calculated and measured airborne and impact sound insulation.     

Detection of Coronary Artery Disease Using Multi-Domain Feature Fusion of Multi-Channel Heart Sound Signals

Heart sound signals reflect valuable information about heart condition. Previous studies have suggested that the information contained in single-channel heart sound signals can be used to detect coronary artery disease (CAD). But accuracy based on single-channel heart sound signal is not satisfactory. This paper proposed a method based on multi-domain feature fusion of multi-channel heart sound signals, in which entropy features and cross entropy features are also included. A total of 36 subjects enrolled in the data collection, including 21 CAD patients and 15 non-CAD subjects. For each subject, five-channel heart sound signals were recorded synchronously for 5 min. After data segmentation and quality evaluation, 553 samples were left in the CAD group and 438 samples in the non-CAD group. The time-domain, frequency-domain, entropy, and cross entropy features were extracted. After feature selection, the optimal feature set was fed into the support vector machine for classification. The results showed that from single-channel to multi-channel, the classification accuracy has increased from 78.75% to 86.70%. After adding entropy features and cross entropy features, the classification accuracy continued to increase to 90.92%. The study indicated that the method based on multi-domain feature fusion of multi-channel heart sound signals could provide more information for CAD detection, and entropy features and cross entropy features played an important role in it.     

一种基于特征点提取的扬声器异常声检测方法

针对短时傅里叶变换在扬声器异常声检测中有效信息提取的随机性问题,提出了特征点法在扬声器异常声检测中的应用.此方法基于扬声器经扫频信号激励所得响应信号的短时傅里叶变换时频图,用改进的尺度不变特征转换算法对合格扬声器与异常声扬声器做特征提取,并将多组特征点经分割剔除后叠加组成特征矩阵模板.以合格扬声器样本提取特征曲线阈值构...     

双层加筋结构有源隔声物理机制研究

深入分析双层加筋结构有源隔声的物理机制有助于控制系统的优化设计。用模态叠加法和声振耦合理论对双层加筋有源隔声结构建模。在辐射加筋板声功率最小的控制条件下,从模态耦合的角度对有源隔声的物理本质进行了详细阐述。分析结果表明,由于双层加筋板中筋的耦合作用影响,系统的声能量传输规律及有源隔声机理与现有的模态分析结论相比均发生改变。结合筋的耦合影响,对空腔声场的模态抑制与重构机理进行修正和补充,清晰解释了双层加筋结构有源隔声的物理本质。     

Hand vein recognition based on the connection lines of reference point and feature point

According to the essential characters of the image topology, a new hand vein recognition algorithm based on the connection lines of reference point and feature points is proposed. In this method, the intersection points and the endpoints of the vein image are used as feature points. After the intersection points and the endpoints selected as feature points, the reference point for image matching are extracted from these points. The relative distances between the reference point and the feature points and the angles between the adjacent connections of the reference point and feature points are calculated and used as recognition features. Finally these two features are combined for hand vein recognition. This method can effectively overcome the influence on the recognition results caused by image translation and rotation. Experimental results show that the proposed algorithm is able to achieve hand vein recognition reliably and quickly.     

基于仿生特征模式匹配的海洋动物声信号识别*

针对小数据量的海洋动物声信号混合识别,将声信号同态分析过程中的线性频率转换为Mel频率,得到模拟人耳听觉特性的Mel频率倒谱系数作为声信号的特征。按照声信号所属的物种建立特征模板,使用动态时间规整算法对待识别特征进行分类识别,并对特征库和识别算法进行优化。分别提取了6种鱼类、3种虾类、12种鲸类的Mel频率倒谱系数,为每个物种建立特征模板。分3次对3种、5种、6种鱼类进行识别,分别获得了100%、96.25%、94.68%的识别率。对6种鱼类、3种虾类、12种鲸类共21个物种进行混合识别,总识别率由87.56%提升至优化后的88.96%。实验结果表明,基于Mel频率倒谱系数和动态时间规整算法的海洋动物声信号混合识别能够在小数据量时获得较高的识别率,优化后的特征库和识别算法能够提升识别率。     

冲击阻尼板的尺寸辨识与声线索提取

针对冲击板的物理属性辨识问题,研究了尺寸辨识的恒定声线索提取及其在听觉感知中所起的作用。设计并完成了三组主观评价实验,实验1分析了录音和合成声作为声刺激对尺寸辨识的影响。实验2和实验3分别针对铝板和木板的冲击声,通过不相似主观评价实验获得尺寸辨识的感知空间和对应力学空间维度,计算了不同声特征的信息精确度。最后,对比实验2和实验3的结果给出了尺寸辨识的恒定声线索,根据声线索与感知结果的相关性分析了听者的尺寸感知策略。结果表明,听者利用录音和合成声均获得了较好的尺寸辨识结果,且听者趋向于利用与尺寸有关的恒定声线索来完成感知任务,而忽略那些容易受其他声源属性影响的声信息。     

Thermal feature extraction of servers in a datacenter using thermal image registration

Thermal cameras provide fine-grained thermal information that enhances monitoring and enables automatic thermal management in large datacenters. Recent approaches employing mobile robots or thermal camera networks can already identify the physical locations of hot spots. Other distribution information used to optimize datacenter management can also be obtained automatically using pattern recognition technology. However, most of the features extracted from thermal images, such as shape and gradient, may be affected by changes in the position and direction of the thermal camera. This paper presents a method for extracting the thermal features of a hot spot or a server in a container datacenter. First, thermal and visual images are registered based on textural characteristics extracted from images acquired in datacenters. Then, the thermal distribution of each server is standardized. The features of a hot spot or server extracted from the standard distribution can reduce the impact of camera position and direction. The results of experiments show that image registration is efficient for aligning the corresponding visual and thermal images in the datacenter, and the standardization procedure reduces the impacts of camera position and direction on hot spot or server features.     

流形学习在运动声源声特征提取方面的研究*

运动声源因声信号时变性、叠加性和空时耦合性强,声数据呈现高维、非线性等特点,使得关键声特征提取困难,声特征提取方法复杂度高、数值计算量大、有效性差。因此,如何有效提取声特征并降低提取方法复杂度成为目前多源声场声源精准识别需迫切解决的关键科学问题。由此,该文提出短时傅里叶变换(STFT)和局部线性嵌入算法(LLE)联合的STFT-LLE流形学习声特征提取方法,并将此方法应用于运动声特征提取,且通过仿真实验测试对其进行了验证。该方法为运动声目标的分类识别提供了技术支撑。     

Point and transfer mobility of point-connected ribbed plates

The work reported in this paper addresses the problem of structure-borne sound transmission between vibrating sources and ribbed-plate receiver structures. Vibrating sources, such as pumps, motors, fans, etc., transmit vibro-acoustic power, causing noise complaints by occupants in cars, trains, aircraft, buildings and/or material fatigue and damage. The transmission process is complicated in that sources transmit power through several contacts and by up to six components of excitation at each contact. The structure-borne sound power is a function of source activity, source mobility and receiver mobility, and all three quantities must be known to some degree. For non-homogeneous receiver structures, such as thin-plate cavity constructions or lightweight framed constructions, the sheathing plates are typically fastened to the framing members using bolts, screws or spot-welded joints. Hence the resulting system is a point-connected ribbed plate structure and the receiver mobility is expected to vary significantly with position. Since measured receiver data seldom is available for prediction purposes, a method of estimating the point and transfer mobility of point connected ribbed plates is required. In this paper, an approximate approach, based on substitution forces, is described. The model uses infinite beam and infinite plate behaviour as input quantities. Estimates of point and transfer mobility are compared with measured results using a timber joist floor construction as an example.     

圈养瓶鼻海豚通讯信号分析及融合分类方法

针对圈养条件下瓶鼻海豚通讯信号（whistle）分类时混叠大量回声定位信号（click）导致分类正确率降低的问题,提出了一种基于机器学习的融合分类方法。分别提取whistle信号的时频分布特征训练随机森林分类器,梅尔时频图特征训练卷积神经网络分类器,在此基础上设计融合判决器对混叠whistle信号进行分类识别。对圈养海豚声信号采集实验数据的分类识别结果表明,融合分类方法具有更好的分类性能,对混叠whistle信号分类正确率大于94%,优于时频分布特征分类器和梅尔时频图特征分类器,能够提高混叠信号的分类能力。     

基于改进HOG特征提取的车型识别算法

本文针对高速环境下的车型识别问题,提出基于方向可控滤波器的改进HOG算法。将方向可控滤波器算法与HOG算法相结合,以实现对车辆图像特征提取。采用主成分分析算法(PCA)约减特征向量维数以减少计算复杂度,利用支持向量机算法对提取特征进行样本训练,实现对车辆外型特征的识别。仿真实验结果表明:采用该算法原始车辆车型的识别正确率均值达到92.36%;另外,本文方法的识别速度比传统的HOG特征算法提高了3.45%,识别实时性得到提升。本文算法比传统HOG算法更优,能有效提高车型识别的效率。     

倒谱参数稀疏分解下的汉语音谎言检测

为了提高汉语语音的谎言检测准确率,提出了一种对信号倒谱参数进行稀疏分解的方法。首先,采用小波包滤波器组对语音信号进行多频带划分,求得子频带对数能量并进行离散余弦变换以提取小波包频带倒谱系数,结合梅尔频率谱系数得到倒谱参数;其次,依据K-奇异值分解方法分别利用说谎和非说谎两种状态下的语音倒谱参数集训练得到过完备混合字典,在此字典上根据正交匹配追踪算法对参数集进行稀疏编码提取稀疏特征;最终进行多种分类模型下的识别实验·实验结果表明,稀疏分解方法相比传统参数降维方法具有更好的优化性能,本文推荐的稀疏谱特征最佳识别率达到78.34%,优于其他特征参数,显著提高了谎言检测识别准确率。