Geographic Information Systems (GIS) have been recognised as a powerful means to integrate and analyse data from various sources in the context of comprehensive floodplain management. As part of this comprehensive approach to floodplain management, it is very important to be able to predict the consequences of different scenarios in terms of flooded areas and associated risk. Hydrologic and hydraulic modelling plays a crucial role and there is much to gain in incorporating these modelling capabilities in GIS. This is still a rather complex task and research is being done on the full integration of these models. Interfacing between these models and GIS may be a very efficient way of overcoming the difficulties and getting very good results in terms of engineering practice. This paper presents results based on the use of Intergraph GIS coupled with Idrisi GIS. Using these two systems substantially increased the flexibility of using GIS as a tool for flood studies. A lumped (XSRAIN) and a distributed (OMEGA) hydrologic models were used to simulate flood hydrographs. The well known HEC-2 Hydraulic model was used to compute flooded areas. These models were applied in the Livramento catchment with very good results. The computation of flooded areas for different flood scenarios, and its representation in GIS, can be used in the assessment of affected property and associated damages. This is a very useful GIS-based approach to floodplain management. 相似文献
We focus on two aspects of the face recognition, feature extraction and classification. We propose a two component system, introducing Lattice Independent Component Analysis (LICA) for feature extraction and Extreme Learning Machines (ELM) for classification. In previous works we have proposed LICA for a variety of image processing tasks. The first step of LICA is to identify strong lattice independent components from the data. In the second step, the set of strong lattice independent vector are used for linear unmixing of the data, obtaining a vector of abundance coefficients. The resulting abundance values are used as features for classification, specifically for face recognition. Extreme Learning Machines are accurate and fast-learning innovative classification methods based on the random generation of the input-to-hidden-units weights followed by the resolution of the linear equations to obtain the hidden-to-output weights. The LICA-ELM system has been tested against state-of-the-art feature extraction methods and classifiers, outperforming them when performing cross-validation on four large unbalanced face databases. 相似文献
To investigate species-specific decomposition rates of litter from native (Quercus faginea) and introduced (Eucalyptus globulus) tree species in Portugal, we monitored changes in the phenolic signature of leaf litter during decomposition as mediated by an aquatic, Proasellus coxalis (Isopoda: Asellota), and two terrestrial, Porcellio dispar and Eluma caelatum (Isopoda: Oniscidea), detritivores. Although the litter of Eucalyptus and Quercus did not differ in overall protein precipitation capacity, we detected differences in terms of contents of particular phenolic compounds and phenol oxidation products. Accordingly, we observed food-specific consumption rates in Proasellus, but not in the terrestrial isopods. Proasellus digested Eucalyptus at significantly higher rates than Quercus, whereas the opposite was the case for Eluma, and Porcellio digested both litter types equally well. Despite slight differences in detail, effects of Proasellus on changes in the signature of litter phenolics were similar for both litter types, whereas terrestrial isopods—Porcellio and Eluma, although they differed from each other—digestively degraded phenolic compounds in Eucalyptus and Quercus litter, respectively, in different ways. Overall, however, degradation of litter phenolics was similarly effective on both litter types. From these data, we conclude that decomposition of Eucalyptus litter does not proceed more slowly than of litter from native Portuguese trees. 相似文献
Decision recommendations are a set of alternative options for clinical decisions (e.g., diagnosis, prognosis, treatment selection, follow-up, and prevention) that are provided to decision makers by knowledge-based Clinical Decision Support Systems (k-CDSS) as aids. We propose to follow a “reasoning over domain” approach for the generation of decision recommendations by gathering and inferring conclusions from production rules. In order to rationalize our approach, we present a specification that will sustain the logic models supported in the knowledge bases we use for persistence. We introduce first the underlying knowledge model and then the necessary extensions that will convey toward the solution of the reported needs. The starting point of our approach is the proposition of Reflexive Ontologies (RO). Here, we go a step further, proposing an extension of RO that includes the handling and reasoning that production rules provide. Our approach speeds up the recommendation generation process. 相似文献
In this paper, we describe the first practical application of two methods, which bridge the gap between the non-expert user
and machine learning models. The first is a method for explaining classifiers’ predictions, which provides the user with additional
information about the decision-making process of a classifier. The second is a reliability estimation methodology for regression
predictions, which helps the users to decide to what extent to trust a particular prediction. Both methods are successfully
applied to a novel breast cancer recurrence prediction data set and the results are evaluated by expert oncologists. 相似文献
Widespread use of GPS and similar technologies makes it possible to collect extensive amounts of trajectory data. These data sets are essential for reasonable decision making in various application domains. Additional information, such as events taking place along a trajectory, makes data analysis challenging, due to data size and complexity. We present an integrated solution for interactive visual analysis and exploration of events along trajectories data. Our approach supports analysis of event sequences at three different levels of abstraction, namely spatial, temporal, and events themselves. Customized views as well as standard views are combined to form a coordinated multiple views system. In addition to trajectories and events, we include on-the-fly derived data in the analysis. We evaluate our integrated solution using the IEEE VAST 2015 Challenge data set. A successful detection and characterization of malicious activity indicate the usefulness and efficiency of the presented approach. 相似文献
The paper addresses the problem of e-customer behavior characterization based on Web server log data. We describe user sessions with the number of session features and aim to identify the features indicating a high probability of making a purchase for two customer groups: traditional customers and innovative customers. We discuss our approach aimed at assessing a purchase probability in a user session depending on categories of viewed products and session features. We apply association rule mining to real online bookstore data. The results show differences in factors indicating a high purchase probability in session for both customer types. The discovered association rules allow us to formulate some predictions for the online store, e.g. that a logged user who has viewed only traditional, printed books, has been staying in the store from 10 to 25 min, and has opened between 30 and 75 pages, will decide to confirm a purchase with the probability of more than 92 %.