基于SVR的船舶溢油事故预测

船舶溢油事故的预测,是确定所需应急资源多少的重要依据;但船舶溢油事故具有小样本性,传统预测方法不再适用。针对船舶溢油事故的小样本性,该文选择SVR模型对其进行预测;SVR算法的关键是核函数的选择及自由参数的确定,针对上述问题该文分别采用交叉验证法、遗传算法;并在matlab软件上建立SVR模型,最后将该模型应用于上海港水域船舶溢油事故的预测。     

微生物处理技术在有机污染物降解中的应用

微生物处理有机污染物是一种费用低,效果好,无二次污染且操作简单的处理方法。综述了国内外几种微生物处理有机污染物技术的研究进展。     

Effect of biogeographic history on population vulnerability in European amphibians

The genetic diversity of populations, which contributes greatly to their adaptive potential, is negatively affected by anthropogenic habitat fragmentation and destruction. However, continental‐scale losses of genetic diversity also resulted from the population expansions that followed the end of the last glaciation, an element that is rarely considered in a conservation context. We addressed this issue in a meta‐analysis in which we compared the spatial patterns of vulnerability of 18 widespread European amphibians in light of phylogeographic histories (glacial refugia and postglacial routes) and anthropogenic disturbances. Conservation statuses significantly worsened with distances from refugia, particularly in the context of industrial agriculture; human population density also had a negative effect. These findings suggest that features associated with the loss of genetic diversity in post‐glacial amphibian populations (such as enhanced fixation load or depressed adaptive potential) may increase their susceptibility to current threats (e.g., habitat fragmentation and pesticide use). We propose that the phylogeographic status of populations (i.e., refugial vs. post‐glacial) should be considered in conservation assessments for regional and national red lists.     

Assessing the components of adaptive capacity to improve conservation and management efforts under global change

Natural‐resource managers and other conservation practitioners are under unprecedented pressure to categorize and quantify the vulnerability of natural systems based on assessment of the exposure, sensitivity, and adaptive capacity of species to climate change. Despite the urgent need for these assessments, neither the theoretical basis of adaptive capacity nor the practical issues underlying its quantification has been articulated in a manner that is directly applicable to natural‐resource management. Both are critical for researchers, managers, and other conservation practitioners to develop reliable strategies for assessing adaptive capacity. Drawing from principles of classical and contemporary research and examples from terrestrial, marine, plant, and animal systems, we examined broadly the theory behind the concept of adaptive capacity. We then considered how interdisciplinary, trait‐ and triage‐based approaches encompassing the oft‐overlooked interactions among components of adaptive capacity can be used to identify species and populations likely to have higher (or lower) adaptive capacity. We identified the challenges and value of such endeavors and argue for a concerted interdisciplinary research approach that combines ecology, ecological genetics, and eco‐physiology to reflect the interacting components of adaptive capacity. We aimed to provide a basis for constructive discussion between natural‐resource managers and researchers, discussions urgently needed to identify research directions that will deliver answers to real‐world questions facing resource managers, other conservation practitioners, and policy makers. Directing research to both seek general patterns and identify ways to facilitate adaptive capacity of key species and populations within species, will enable conservation ecologists and resource managers to maximize returns on research and management investment and arrive at novel and dynamic management and policy decisions.     

Implications of genetics and current protected areas for conservation of 5 endangered primates in China

Most of China's 24–28 primate species are threatened with extinction. Habitat reduction and fragmentation are perhaps the greatest threats. We used published data from a conservation genetics study of 5 endangered primates in China (Rhinopithecus roxellana, R. bieti, R. brelichi, Trachypithecus francoisi, and T. leucocephalus); distribution data on these species; and the distribution, area, and location of protected areas to inform conservation strategies for these primates. All 5 species were separated into subpopulations with unique genetic components. Gene flow appeared to be strongly impeded by agricultural land, meadows used for grazing, highways, and humans dwellings. Most species declined severely or diverged concurrently as human population and crop land cover increased. Nature reserves were not evenly distributed across subpopulations with unique genetic backgrounds. Certain small subpopulations were severely fragmented and had higher extinction risk than others. Primate mobility is limited and their genetic structure is strong and susceptible to substantial loss of diversity due to local extinction. Thus, to maximize preservation of genetic diversity in all these primate species, our results suggest protection is required for all sub‐populations. Key priorities for their conservation include maintaining R. roxellana in Shennongjia national reserve, subpopulations S4 and S5 of R. bieti and of R. brelichi in Fanjingshan national reserve, subpopulation CGX of T. francoisi in central Guangxi Province, and all 3 T. leucocephalus sub‐populations in central Guangxi Province.     

Optimizing mixture properties of biodiesel production using genetic algorithm-based evolutionary support vector machine

Nowadays, biodiesel is used as one of the alternative renewable energy due to the increasing energy demand. However, optimum production of biodiesel still requires a huge number of expensive and time-consuming laboratory tests. To address the problem, this research develops a novel Genetic Algorithm-based Evolutionary Support Vector Machine (GA-ESIM). The GA-ESIM is an Artificial Intelligence (AI)-based tool that combines K-means Chaotic Genetic Algorithm (KCGA) and Evolutionary Support Vector Machine Inference Model (ESIM). The ESIM is utilized as a supervised learning technique to establish a highly accurate prediction model between the input--output of biodiesel mixture properties; and the KCGA is used to perform the simulation to obtain the optimum mixture properties based on the prediction model. A real biodiesel experimental data is provided to validate the GA-ESIM performance. Our simulation results demonstrate that the GA-ESIM establishes a prediction model with better accuracy than other AI-based tool and thus obtains the mixture properties with the biodiesel yield of 99.9%, higher than the best experimental data record, 97.4%.     

基于遗传神经网络的除湿机故障诊断与寿命预测

目的识别除湿机的性能状态和预测吸附剂的剩余寿命。方法针对除湿机故障过程缓变的特点,提出一种基于数据驱动的遗传神经网络模型。首先,为解决设备失效程度划分模糊的问题,由5个热力参数组成反映吸附剂劣化程度的特征向量,关联分析得到除湿机的5类故障模式。其次,利用遗传神经网络建立状态参数和故障模式的映射关系。最后,对表征设备吸附能力的主参数进行外推预测。结果训练好的诊断网络可准确地识别出设备的劣化程度及其演变过程,预测网络的预测精度非常高。结论该方法可有效地实现对除湿机的故障诊断与预测。。     

回采工作面瓦斯涌出量遗传投影寻踪回归预测

为快速、准确预测回采工作面瓦斯涌出量,基于投影降维思想,建立一种遗传算法(GA)投影寻踪回归预测方法。选取煤层瓦斯原始含量、埋藏深度、煤层厚度、煤层倾角、工作面长度、推进速度、采出率、临近层瓦斯含量、临近层厚度、临近层层间距、岩层岩性、开采深度作为评价因子,对某矿15个学习样本进行训练,建立GA投影寻踪回归预测模型。利用该矿3个实测样本对模型进行检验,并与主成分分析和BP神经网络方法结果进行对比。研究表明:利用GA投影寻踪回归预测回采工作面瓦斯涌出量,平均误差为3.43%,最大误差为5.7%,精度优于其他2种方法。     

响应面法和神经网络优化Acinetobactersp．DNS32发酵基质

为了提高阿特拉津降解菌Acinetobactersp．DNS32的产量，分别采用响应曲面法和基于人工神经网络的遗传算法对阿特拉津降解菌DNS32发酵培养基中3个重要基质成分（玉米粉、豆饼粉、K：HPO。）进行优化研究。响应曲面法确定3种成分的含量为玉米粉39．494g／L，豆饼粉25．638g／L和K。HPO。3．265g／L时，预测发酵活菌最大生物量为7．079×10^8CFU／mL，实测量为7．194×10^8CFU／mL；人工神经网络结合遗传算法优化确定3种主要成分含量为玉米粉为39．650g／L，豆饼粉为25．500g／L，K2HPO4为2．624g／L时，预测最大值为7．199×10^8CFU／mL，实测量为7．244×10。CFU／mL；最终确定培养基配方：玉米粉为39．650g／L，豆饼粉为25．500g／L，K2HPO4为2．624g／L，CaCO3为3．000g／L，MgSO4·7H2O和NaCl均为0．200g／L；优化后阿特拉津降解菌DNS32发酵生物量比优化前提高了36．6％。结果表明，在阿特拉津降解菌DNS32发酵培养基组分优化方面，响应面法和基于人工神经网络的遗传算法都是可行的，基于人工神经网络的遗传算法具有更好的拟合度和预测准确度。     

煤炭产业国际竞争力的遗传—投影寻踪评价

根据煤炭产业发展的实际状况,提出了煤炭产业竞争力评价的指标体系。采用探索性数据分析—投影寻踪法,结合遗传算法,建立了遗传—投影寻踪综合评价模型。以全球11个主要产煤国为对象进行了实证研究,验证了该方法的科学性和实践的可行性,提出提升我国煤炭产业竞争力的对策建议。