A spatio‐temporal water quality assessment of the Beas and Sutlej Rivers at the Harike Wetland: A Ramsar site in Punjab,India

Lakes play a vital role in regulating water storage, flow of river water, and ultimately maintaining a balanced ecosystem. Spatial and temporal variations in physicochemical parameters of water in Harike Wetland, a Ramsar site in the northwestern state of Punjab, India, were studied. This study was conducted on a monthly basis from January to December 2015. The water quality was studied at ten locations from sites 1 to 10 upstream, central and downstream from Harike Lake for ten physicochemical parameters, including temperature, pH, electrical conductivity, turbidity, dissolved oxygen concentration biological oxygen demand, nitrate and phosphate concentrations and salinity. The findings of this study revealed that, except for temperature and pH, all parameters exhibited relatively higher values for the Sutlej River, compared with the Beas River, with sampling sites 5 to site 7 exhibiting intermediate results. The mean seasonal temperature variations ranged from 16.9 to 26.6 °C, the pH from 7.7 to 8.2, electrical conductivity from 223 to 303 μS cm^?1 and TDS concentration from 148.7 to 180.4 ppm. Correlation analysis was conducted to assess the relations between the variables. The electrical conductivity exhibited a high positive correlation with salinity and biological oxygen demand, whereas it correlated negatively with the dissolved oxygen concentration. Box and whisker plots were also plotted for the study results to better examine the data distribution.     

HMM-based state classification of a user with a walking support system using visual PCA features

The improvement of safety and dependability in systems that physically interact with humans requires investigation with respect to the possible states of the user’s motion and an attempt to recognize these states. In this study, we propose a method for real-time visual state classification of a user with a walking support system. The visual features are extracted using principal component analysis and classification is performed by hidden Markov models, both for real-time fall detection (one-class classification) and real-time state recognition (multi-class classification). The algorithms are used in experiments with a passive-type walker robot called “RT Walker” equipped with servo brakes and a depth sensor (Microsoft Kinect). The experiments are performed with 10 subjects, including an experienced physiotherapist who can imitate the walking pattern of the elderly and people with disabilities. The results of the state classification can be used to improve fall-prevention control algorithms for walking support systems. The proposed method can also be used for other vision-based classification applications, which require real-time abnormality detection or state recognition.     

The annual cycle of Flehmen in black-tailed deer (Odocoileus hemionus columbianus)

Flehmen is a stereotyped response of ungulates and other mammals to urine. In black-tailed deer, Flehmen occurs typically in males (rarely in females), and its frequency shows an annual cycle. Flehmen in response to female urine was most frequent in November, and to male urine in January. The response minimum to both types of urine occurred in May. Fifty-five to 100% of initial responses to female urine resulted in Flehmen. The deer responded more often to female urine, and the difference between the responses to female and male urine increased from May to November. A male's own urine released Flehmen more often than did urine of other males. The response intensity varied with the spatial orientation of the male to the urinating female, and responses were usually limited to distances of 15 m or less.     

A new approach of audio emotion recognition

A new architecture of intelligent audio emotion recognition is proposed in this paper. It fully utilizes both prosodic and spectral features in its design. It has two main paths in parallel and can recognize 6 emotions. Path 1 is designed based on intensive analysis of different prosodic features. Significant prosodic features are identified to differentiate emotions. Path 2 is designed based on research analysis on spectral features. Extraction of Mel-Frequency Cepstral Coefficient (MFCC) feature is then followed by Bi-directional Principle Component Analysis (BDPCA), Linear Discriminant Analysis (LDA) and Radial Basis Function (RBF) neural classification. This path has 3 parallel BDPCA + LDA + RBF sub-paths structure and each handles two emotions. Fusion modules are also proposed for weights assignment and decision making. The performance of the proposed architecture is evaluated on eNTERFACE’05 and RML databases. Simulation results and comparison have revealed good performance of the proposed recognizer.     

基于类标记扩展的半监督网络流量特征选择算法

针对网络流量特征选择过程中存在的样本标记瓶颈问题,以及现有半监督方法无法选择强相关的特征的不足,提出一种基于类标记扩展的多类半监督特征选择(SFSEL)算法。该算法首先从少量的标记样本出发,通过K-means算法对未标记样本进行类标记扩展;然后结合基于双重正则的支持向量机(MDrSVM)算法实现多类数据的特征选择。与半监督特征选择算法Spectral、PCFRSC和SEFR在Moore数据集进行了对比实验,SFSEL得到的分类准确率和召回率明显都要高于其他算法,而且SFSEL算法选择的特征个数明显少于其他算法。实验结果表明: SFSEL算法能够有效地提高所选特征的相关性,获取更好的网络流量分类性能。     

一类考虑病毒发生变异的SIS疾病传播模型

为了研究变异行为对病毒传播的影响,提出了一个病毒发生变异的疾病传播模型,在模型中考虑了两种病毒相互转换的过程,计算机模拟结果表明,两种病毒的稳态感染比例与它们之间的相互转换概率γ1和γ2有关,当γ1＞0且γ2=0时,I1型感染者将消失,当γ1与γ2都大于0时,I1/I2与γ1/γ2成反比,且与α1/β1和α2/β2的取值无关.研究还发现病毒变异时由于缺乏对应的治疗药物和措施而出现一段真空期,这导致变异病毒的感染比例快速增加,但真空期的出现只能增加感染者的瞬时感染比例,而对稳态感染比例没有影响.该研究对人们深入理解病毒传播机理具有启发作用.     

基于局部重构的无监督特征选择方法

利用局部线性嵌入(LLE)算法中获得局部邻域之间的重构关系与使用最小角回归方法解决L1归一化问题都使用回归方法,针对在通过映射获得低维嵌入空间与通过特征选择获得低维空间上有着一致的思想,提出一种能保持局部重构关系的无监督谱特征选择方法.该方法利用最小二乘法计算样本的邻域重构系数,并用这些系数表示样本之间的关系,通过解决稀疏特征值问题获得能够保持样本间关系的低维嵌入空间,最后通过解决L1归一化问题实现自动特征选择.通过在四个不同数据集上的聚类实验结果证明,该方法能更准确地评价每个特征的重要性,能自动适应不同的数据集,受参数影响更小,可以明显提升聚类效果.     

基于文档文字特征的碎纸机碎片拼接算法

针对经碎纸机粉碎的文档碎片,提出拼接复原的模型并研制了相应的算法。首先研究文档碎片边界像素特征,据此提出碎片横向拼接的两种算法;然后,研究行高、字体间间距以及字体大小等文本特征,据此提出针对经横向拼接形成的水平残条的纵向拼接算法。最后根据算法编写Matlab程序,并进行实验,结果表明该算法效果良好。     

采用主监视窗扩展技术的增强现实三维注册方法

在增强现实三维注册中,采用重新检测策略时顿卡现象严重。提出一种采用主监视窗扩展技术的增强现实三维注册方法。在检测阶段,引入特征点可信度和主监视窗,并设计主监视窗的分割、扩展和调控策略,大幅提升了计算速度;在跟踪阶段,采用基于图像金字塔的光流算法进行特征点跟踪。实验证明,该方法不仅有效缓解了顿卡现象,也提升了系统整体的实时性。     

LDE融合光谱回归分类的光照变化人脸识别

针对光照变化人脸识别问题中传统的光谱回归算法不能很好地进行特征提取而严重影响识别性能的问题,提出了局部判别嵌入优化光谱回归分类的人脸识别算法。计算出训练样本的特征向量;借助于数据的近邻和分类关系,利用局部判别嵌入算法构建分类问题所需的嵌入,同时学习每种分类的子流形所需的嵌入;利用光谱回归分类算法计算投影矩阵,并利用最近邻分类器完成人脸的识别。在两大人脸数据库扩展YaleB及CMU PIE上的实验验证了该算法的有效性,实验结果表明,相比其他光谱回归算法,该算法取得了更高的识别率、更好的工作特性,并且降低了计算复杂度。