基于熵权-属性识别模型的地表水质量评价

利用熵权法并结合属性识别理论,建立了熵权-属性识别模型。采用地表水环境质量标准（GB3838—2002）作为依据,选用7个影响因子作为评价指标,利用熵权法确定各评价指标的权重以计算综合属性测度区间,应用置信度准则和评分准则对地表水质量进行属性识别。实例研究表明,该模型能有效地解决地表水质量评价的问题,评价模型采用熵权法确定权重,避免了权重确定中的主观性和随意性,保证了评价工作的客观性和准确性。     

天然气集输站泄漏监控系统研究

为克服目前天然气集输站站控系统存在的主要技术问题,探讨了建立泄漏监控安全系统的技术要求.该系统应用负压波检漏技术、模式识别技术和虚拟仪器技术,实现了.对天然气泄漏的信号检测、处理、传输和实时动态显示等.借助于这些技术开发的天然气泄漏监控系统,具有数据处理准确可靠,精度高,误报率低等特点.通过该系统,可以及时获取相关参数和信息,实现早期预警,降低天然气泄漏的事故风险.     

The Integration of a Genetic Programming-Based Feature Optimizer With Fisher Criterion and Pattern Recognition Techniques to Non-Intrusive Load Monitoring for Load Identification

Identification of electricity energy consumption on individual household appliances used in a smart house is the first important step for making the use and conservation of electricity energy more efficient. In the past, Non-Intrusive Load Monitoring (NILM) techniques, which are part of smart grid techniques realized to improve electricity energy usage efficiency, have been developed to identify individual appliances with avoiding installing many smart meters for appliances in a field. In this paper, a new NILM technique that integrates an efficient Genetic Programming (GP)-based feature optimizer with pattern recognition techniques is proposed to identify which appliance is being turned on or off. The proposed GP-based feature optimizer with Fisher criterion is used to generate a more efficient feature than original potential transient features extracted from captured transient response of household appliances through analysis of NILM. The new feature generated by GP is used by pattern recognition techniques as load identifiers for load identification. The load identifiers used and compared in this paper include k-Nearest-Neighbor Rule, Back-Propagation Artificial Neural Network, and Learning Vector Quantization. Experiments are conducted under different single-load and multiple-load operation circumstances at different actual experimental environments with small disturbances. As shown from the experimental results, the proposed is confirmed to be feasible and usable.     

遥感震害快速评估技术在汶川地震中的应用

2008年5月12日四川汶川8.0级大地震发生后,在地面交通严重受阻、通信中断的情况下,遥感技术成为了地震灾情获取、地震应急和震后快速评估的重要手段。提出了利用高分辨率遥感影像进行地震应急和震后快速评估的技术流程,该流程涉及到遥感影像的数据管理、快速校正、图像增强、震害信息提取、地震灾情快速评估和评估结果网络发布等关键技术。利用遥感震害识别和快速评估技术准确提取了汶川地震的震害信息,绘制的基于遥感数据的汶川地震烈度分布图与中国地震局公布的基于地面调查结果的地震烈度分布图非常接近,首次实现了在震害遥感影像获取后的2~6h内,提供准确的宏观灾情分布情况以及初步的地震损失评估结果,在汶川地震的灾情获取、地震应急和震后快速评估中发挥了重要的作用。     

支持向量机法在煤与瓦斯突出分析中的应用研究

通过分析采煤工作面煤与瓦斯涌出量与地质构造指标的对应关系,应用支持向量机(SVM)方法对煤与瓦斯涌出类型及涌出量进行分析。建立两类突出识别的SVM模型、多类型突出识别的H-SVMs模型以及预测瓦斯涌出量的支持向量回归模型。研究结果表明:SVM方法能够很好地对煤与瓦斯突出模式进行识别,所建立的采煤工作面瓦斯涌出量预测模型的精度高于应用BP神经网络预测精度;SVM理论基础严谨,决策函数结构简单,泛化能力强,并且决策函数中的法向量W可以反映突出模式识别的地质结构指标的权重。     

Schooling decisions in guppies (Poecilia reticulata) are based on familiarity rather than kin recognition by phenotype matching

Evidence from a number of freshwater species indicates that fish prefer to school with familiar individuals. Do they also choose to associate with kin? Our experiment tested this idea using the Trinidadian guppy, Poecilia reticulata, a species whose reproductive biology favours the association of kin groups. Juveniles reared together were able to recognise one another on the basis of either visual or chemical cues, but showed no preference for schooling with unfamiliar kin. We therefore conclude that any naturally occurring kin groups in this species will occur as a result of familiarity rather than as a consequence of kin recognition based on phenotype matching.     

Sensory complementation and the acquisition of predator recognition by salmonid fishes

Following disturbance, some aquatic prey species release chemicals that act as a warning cue and increase vigilance in nearby conspecifics. Such disturbance cues evoke consistent low intensity anti-predator responses. In contrast, alarm cues from injured conspecifics often evoke stronger intensity responses in prey animals. In this study, we test the sensory complement hypothesis, which suggests that multiple cues act in an additive or synergistic fashion to provide additional information for risk assessment by prey. In the first experiment, we showed that juvenile rainbow trout pre-exposed to disturbance cues respond to a given concentration of damage-released alarm cues with a higher intensity of response than the trout that were pre-exposed to cues from undisturbed conspecifics. The two cues acted in an additive fashion. In the second experiment, we demonstrated that disturbance cues alone were not enough to elicit a conditioned response to the odour of a novel predator. We also showed that while disturbance cues elicit an increase in the response of trout to alarm cues, this increase does not translate into a stronger learned response to the predator when the predator odour is paired with alarm cues. Future studies should take into account sensory complementation to avoid underestimating the responses of prey to predators.     

改进属性识别模型及其在城市环境质量综合评价中的应用

应用属性识别模型进行综合评价时,评价指标权重向量的计算具有一定的主观性。据此提出基于数据驱动技术的改进方法以使权重的确定更趋合理。实例说明,改进的属性识别模型不仅原理直观,评价结果准确,而且计算简便,在复杂系统综合评价中具有较广的适用性。     

地震前兆混沌时间序列多尺度分维异常识别研究

对地震前兆观测时间序列的混沌性态及其产生的根源进行了探讨。根据小波变换良好的时、频局部化特征和分形维数的变化特征,从小波分析多尺度分解的角度出发结合分形理论探讨了地震前兆混沌时间序列的异常识别问题。对几个实例的研究表明,大多数时间段内时间序列小波变换系数的分维—尺度变化曲线呈光滑、缓慢减小变化,有异常信息时段的时间序列小波变换系数的分维—尺度变化曲线变化的主要特点是曲线具有峰值,并出现了曲线先是由高向低,然后再由低向高变化,在某一尺度处达到峰值后再缓慢减小的情况。异常出现的时间在震前约2个月至1年。将小波变换与分形理论结合起来研究地震问题,不仅开拓了地震科学研究的新领域,同时也是对小波变换及分形理论应用的延拓。     

Threat-sensitive generalization of predator recognition by larval amphibians

Despite the importance of acquired predator recognition in mediating predator–prey interactions, we know little about the specific characteristics that prey use to distinguish predators from non-predators. Recent experiments with mammals and fish indicate that some prey lacking innate predator recognition have the ability to display anti-predator responses upon their first encounter with those predators if they are similar to predators that the prey has recently learned to recognize. This phenomenon is referred to as generalization of predator recognition. In this experiment, we documented for the first time that larval amphibians (woodfrog, Rana sylvatica) have the ability to generalize the recognition of known predators to closely related novel predators. Moreover, we demonstrated that this ability is dependent on the level of risk associated with the known predator. When red-bellied newt, Cynops pyrrhogaster (known predator), was paired with simulated low risk, tadpoles displayed fright responses to newts and novel tiger salamanders, Ambystoma tigrinum, but not to novel African clawed frogs, Xenopus laevis. However, when the newt was paired with simulated high risk, tadpoles generalized their responses to both tiger salamanders and African clawed frogs. Larval anurans seem to have a wider generalization frame than other animals.