乌鲁木齐城市群城市间大气污染相互影响分析

利用乌鲁木齐城市群2010—2015年空气质量日报,引入时间序列的VAR模型对城市间的大气污染相互影响关系及贡献进行研究。结果表明:乌鲁木齐城市群5市存在影响效应,乌鲁木齐受外源影响为主,昌吉、阜康受内源影响为主,五家渠、石河子受内外源共同影响;乌鲁木齐城市群城市间大气污染相互影响存在明显的滞后效应,前3期的影响最大,第10期以后响应值趋于0。     

Development of a method for comprehensive water quality forecasting and its application in Miyun reservoir of Beijing, China

Water quality forecasting is an essential part of water resource management. Spatiotemporal variations of water quality and their inherent constraints make it very complex. This study explored a data-based method for short-term water quality forecasting. Prediction of water quality indicators including dissolved oxygen, chemical oxygen demand by KMnO₄ and ammonia nitrogen using support vector machine was taken as inputs of the particle swarm algorithm based optimal wavelet neural network to forecast the whole status index of water quality. Gubeikou monitoring section of Miyun reservoir in Beijing, China was taken as the study case to examine effectiveness of this approach. The experiment results also revealed that the proposed model has advantages of stability and time reduction in comparison with other data-driven models including traditional BP neural network model, wavelet neural network model and Gradient Boosting Decision Tree model. It can be used as an effective approach to perform short-term comprehensive water quality prediction.     

一种基于LVQ神经网络与图像处理的火焰识别算法

针对传统火灾探测技术存在的不稳定、误判率高等缺点,通过分析室内火灾图像与常见干扰光源图像的特点,提出一种基于人工神经网络的火焰图像检测技术。对火焰图像的基本特性进行分析,利用火焰图像序列的面积重叠率和中心相对移动率以及颜色等信息,结合实现学习向量量化(LVQ)神经网络融合技术,对视频序列图像中火焰的自动检测。仿真试验结果表明,基于LVQ神经网络的信息融合算法的网络收敛速度较快,有较高的火灾火焰识别准确率。     

Environmental refuge from disease-driven amphibian extinction

Species that are tolerant of broad environmental gradients may be less vulnerable to epizootic outbreaks of disease. Chytridriomycosis, caused by the fungus Batrachochytrium dendrobatidis, has been linked to extirpations and extinctions of amphibian species in many regions. The pathogen thrives in cool, moist environments, and high amphibian mortality rates have commonly occurred during chytridiomycosis outbreaks in amphibian populations in high-elevation tropical rainforests. In Australia several high-elevation species, including the armored mist frog (Litoria lorica), which is designated as critically endangered by the International Union for the Conservation of Nature (IUCN), were believed to have gone extinct during chytridiomycosis outbreaks in the 1980s and early 1990s. Species with greater elevational ranges disappeared from higher elevations, but remained common in the lowlands. In June 2008, we surveyed a stream in a high-elevation dry sclerophyll forest and discovered a previously unknown population of L. lorica and a population of the waterfall frog (Litoria nannotis). We conducted 6 additional surveys in June 2008, September 2008, March 2009, and August 2009. Prevalences of B. dendrobatidis infection (number infected per total sampled) were consistently high in frogs (mean 82.5%, minimum 69%) of both species and in tadpoles (100%) during both winter (starting July) and summer (starting February). However, no individuals of either species showed clinical signs of disease, and they remained abundant (3.25 - 8.75 individuals of L. lorica and 6.5-12.5 individuals of L. nannotis found/person/100 m over 13 months). The high-elevation dry sclerophyll site had little canopy cover, low annual precipitation, and a more defined dry season than a nearby rainforest site, where L. nannotis was more negatively affected by chytridiomycosis. We hypothesize this lack of canopy cover allowed the rocks on which frogs perched to warm up, thereby slowing growth and reproduction of the pathogen on the hosts. In addition, we suggest surveys for apparently extinct or rare species should not be limited to core environments.     

青稞B-hordein基因表达载体构建及对小麦的遗传转化

利用从具有特殊B-hordein亚基组成的青藏高原青稞材料中克隆的B-hordein编码基因(SL60)和小麦高分子量谷蛋白亚基胚乳特异表达启动子PGlu1Dx构建了真核表达载体pCB2007-SL60.通过农杆菌介导对普通小麦进行遗传转化,共获得227株再生植株,经PCR鉴定和转化片段测序验证,最终获得5株阳性植株.研究为进一步分析B-hordein基因在小麦背景中的遗传和表达,以及对小麦加工特性的影响奠定了基础.图5表2参21     

羧酸及其衍生物急性毒性的QSAR研究

基于定量结构-活性相关性(QSAR)原理,研究了27种羧酸及其衍生化合物结构与其急性毒性LC50之间的内在定量关系。应用遗传算法从大量结构参数中优化筛选出与LC50最为密切相关的五个参数作为分子描述符,得出影响羧酸及其衍生物急性毒性的主要结构特征为分子的大小及其空间效应等。分别采用支持向量机(SVM)方法和多元线性回归(MLR)方法建立了相应的QSAR预测模型,并对所建模型分别进行了内部验证和外部验证。结果表明,两种模型均具有较高的稳定性、预测能力及泛化性能。其中,支持向量机模型对训练集和预测集样本的预测平均绝对误差分别为0.149和0.211,优于多元线性回归方法所得结果。     

Correction model for CO detection in the coal combustion loss process in mines based on GWO-SVM

Accurate detection of CO gas is crucial to the prevention of coal combustion. Tuneable diode laser absorption spectroscopy (TDLAS) is a reliable method for CO detection during coal combustion. The influences of temperature and pressure cause changes in the line strength and linewidth of the index gases’ absorption spectra, leading to sizable measurement errors. To correct the distortion of the CO absorption spectrum caused by temperature and pressure fluctuation, a compensation model based on the grey wolf optimizer–support vector machine (GWO–SVM) was proposed. The results were compared with those of the single SVM, the back propagation neural network (BPNN), and multiple regression analysis (MRA). MRA was revealed to result in the lowest accuracy, which indicated that MRA is not ideal for compensation in TDLAS. The hyperparameter selection of the SVM had the disadvantages of randomness and blindness, which led to instability and large errors. The BPNN achieved better correction in the training stage, but severe overfitting occurred in the testing stage. The modified results revealed that the GWO–SVM model had higher accuracy and stability than the other models. It effectively inhibited the effects of temperature and pressure on the measured concentration and greatly improved the measurement accuracy. The equipment is thus suitable for CO gas detection with the aim to preventing coal combustion loss, and it can be further applied to loss prevention in other process fields.     

单矢量水听器抗混响方法研究

混响是主动声纳的主要干扰。矢量水听器是较新型的水声测量设备,其接收的混响和目标信号之间存在相位差异。基于这些差异,探索了矢量声能流方法用于抗混响处理的可行性,在理论上得到了较高的空间处理增益和时间处理增益。计算结果和仿真结果表明,相对于常规的声压平方积分器,该方法具有很好的抗混响效果。     

SVM与ANN在湖泊富营养化评价中的对比研究

支持向量机是由Vapnik等提出的建立在统计学习理论基础上的一种新的机器学习方法,由于其使用结构风险最小化原则代替经验风险最小化原则,又由于其应用了核函数思想,它可以较好地解决非线性问题;人工神经网络(ANN)已经较成功解决模式识别和任意非线性函数回归问题,但是存在训练样本不足,并可能出现过拟合现象。SVM的结构风险最小化算法引起了科学界的关注,对传统基于经验风险最小化的神经网络算法提出了挑战,文章介绍了SVM和ANN的基本原理,并对二者在巢湖富营养化水平评价上做对比研究,结果表明,ANN比较容易陷入局部最优,支持向量机评价结果更加符合实际。