以语音识别为基础的音乐检索系统

针对一般的语音识别算法均存在抗噪能力不好的问题,无法满足音乐检索系统的需求。针对于此,本文以抗噪能力为基础对MFCC语音识别算法进行了优化,第一步是通过F比方法加权优化了MFCC算法的特征参数,估计出各维特征分量对识别率的影响,并将其提取出来,然后采用主成分分析法对提取的特征分量进行降维处理,以降低计算复杂度,减少数据存储量,加快训练时间,最终提高识别效率。算法仿真结果表明,本文提出的基于抗噪能力优化的MFCC语音识别算法具有较好的抗噪能力,比传统MFCC算法对音乐检索的精确度更高。     

泸县节水农业发展潜力分析

水在农业发展中起重要作用,发展节水农业是缓解水资源供需矛盾、提高农业综合生产能力的重要途径。建设节水型农业,提高水的有效利用率,坚持节水灌溉、坚持节水农业的发展,不断改善和完善农业生产条件,将促进水资源可持续利用和社会经济可持续发展。本文获取泸县耕地面积、主要农作物种植面积、水资源利用及水利工程变化数据,主要农作物平均灌溉定额和节水灌溉定额数据,运用灰色预测法对泸县未来几年的主要农作物灌溉用水量进行预测,结果显示:2014-2017年水稻、玉米、小麦在采用节水技术后共计用水量分别为:14.2亿m3、11.08亿m3、0.46亿m3,共计节水量分别为:14.04亿m3、11.41亿m3、0.59亿m3。研究得出:应该大力发展节水农业.改进节水技术.提高水的利用率.节约水资源。     

Informing in-season tactical periodisation in team sport: development of a match difficulty index for Super Rugby

In team sports, tactical periodisation refers to the planned manipulation of training loads with the aim of prioritising athlete readiness for matches of greatest importance. Although monitoring of athletes’ physical condition is often used to inform this planning, the direct influence of external factors on match difficulty has not been well quantified. In this study, a ‘match difficulty index’ (MDI) for use in Super Rugby was developed, based on the influence imparted by five external factors on previous match outcomes. Specifically, information relating to match location, days break between matches, time-zone change and opposition ladder position (both current and previous year) were collected for matches played during the 2011–2013 Super Rugby seasons. Logistic regression analyses were used to assess the importance of each of these factors with respect to match outcome (win/loss), with opposition ladder position and match location (home, domestic away or international) exerting the greatest influence on match difficulty. Three separate cross-validated models were constructed, with match outcome classification performance reported as 66.2%, 65.5% and 63.7% respectively. The three MDI models emanating from this study can each be used to inform tactical periodisation program design both prior to and during the regular season.     

高保真录音回放攻击取证算法与仿真验证

针对语音认证系统中高保真录音回放攻击问题,开展了录音回放攻击取证的研究,论述了基于信道模式噪声和回放语音MFCC特征参数提取的取证算法;通过labview软件编程进行仿真验证,提取了疑似回放攻击语音和原始语音信道噪声差值频谱图和疑似回放语音MFCC特征值,结果表明通过提取回放语音中信道模式噪声和MFCC特征参数并设计滤波器去噪能够识别原始语音和高保真录音的差异,为语音司法鉴定和语音认证系统的设计提供了理论依据。     

工程建筑物变形监测数据预测分析

在概述灰色Verhuslt模型基础上,对灰色Verhuslt模型在建筑物沉降监测中的应用做了详细介绍.结合工程实例中4#楼东南角S044点沉降数据建立灰色Verhuslt模型,实证结果表明模型精度可靠,实际沉降量观测值与沉降量预测值吻合较好,在沉降变形分析数据预测分析中应用灰色Verhuslt模型具有可行性.     

基于中值滤波和维纳滤波的图像混合噪声滤波研究

某一种去噪方法通常只对某一类噪声的滤除较为有效,为了抑制混合噪声,提出一种结合中值滤波与维纳滤波的图像去噪算法。该算法首先检测出脉冲噪声点,并对脉冲噪声点进行中值滤波处理,然后用维纳滤波滤除图像中的高斯白噪声。仿真实验表明,对于被高斯、脉冲混合噪声污染的图像,该算法的去噪效果显然比单一的中值滤波和维纳滤波好得多。     

BP神经网络算法在教师履职考评中的应用研究

基于BP神经网络算法在分类预测方面的权威性,提出利用BP神经网络构建教师履职评价模型的新方法。实验结果表明,该模型具有较高的可行性和实用性,能够准确、高效地对教师履职情况进行客观评价。     

Characterization of chaotic multiscale features on the time series of melt index in industrial propylene polymerization system

The chaos characteristics of melt index have been first explored, and the Hilbert–Huang transform method and time delay embedding method are applied to multiscale dynamic analysis on the time series of the melt index (MI) in the propylene polymerization industry. The research results show that the embedding delay is 2, the embedding dimension is 5, the correlation dimension D₂ is 1.57, and the maximum Lyapunov exponent is 0.143 for the melt index series, which provide clear evidence of chaotic multiscale features in the propylene polymerization process. Three intrinsic mode functions (IMFs) are decomposed from the melt index time series; the presence of non-integer fractal correlation dimension and positive finite maximum Lyapunov exponent are found in some IMF components. The PP melt index series are divided into two chaotic signals, a determined signal and a random signal respectively, and its complexity is therefore reduced. Furthermore, the coupling of subscale structures of the propylene polymerization is explored with the dimension of interaction dynamics and a robust algorithm for detecting interdependence. It is found that IMF(2) is the main driver in the coupling system of IMF(1)and IMF(2). All these provide a guideline for studying propylene polymerization process with chaotic multiscale theory and may offer more candidate tools to model and control propylene polymerization system in the future.     

基于智能视觉的假肢虚拟再生仿真技术的算法研究

研究假肢虚拟再生仿真方法。腿部结构较为复杂,残缺再生过程需要根据不同腿部残缺根源部位进行方向和角度的预测,但是由于腿部角度和生长方向推断过程信息过少,造成传统的虚拟腿部残缺再生仿真无法取得足够信息,只能根据简单的向上,造成模拟效果不好。为此,提出了一种基于智能视觉的假肢虚拟再生仿真方法。根据误差四元数状态变换相关理论,能够对假肢虚拟再生的方向和旋转角度进行有效的预测,从而为假肢虚拟再生仿真提供准确的依据。根据双目立测三维模拟方法,建立假肢虚拟再生仿真三维模型。实验结果表明,利用该算法进行假肢虚拟再生仿真,可以真实的反映残肢不同位置特征点的相关性,从而为假肢虚拟再生手术提供依据。     

基于RBF神经网络的成都市城镇建设用地需求预测

以成都市为研究区域,利用城镇建设用地和社会经济统计数据,从因素和时间二维角度出发,分别选用RBF神经网络模型和GM(1,1)模型,在模型比较优选的基础上对成都市城镇建设用地需求进行了预测。结果表明:RBF神经网络模型与GM(1,1)模型相比,前者的平均绝对误差和误差均方根较低,且线性拟合效果更佳,是一种精度较高的预测方法;据预测,近期2015年和远期2020年研究区城镇建设用地需求量将分别达到145 986.10hm2和182 321.26hm2,研究结果既能为具有类似数据"突变"特征的城市开展城镇建设用地需求预测提供方法借鉴,又能为研究区土地资源的可持续利用和土地利用总体规划的定期修编提供决策依据。