Search Results (5)

Regarding high-level and complex decision-making scenarios, the study presents an extensive approach to the Simple Aggregation of Preferences Expressed by Ordinal Vectors-Multi Decision Making method (SAPEVO-M). In this context, the modeling proposal, named SAPEVO-Hybrid and Hierarchical (SAPEVO-H²), the objective of this study, based on the concepts of multi-criteria analysis, provides the evaluation of alternatives under the light of multiple criteria and perceptions, enabling the integration of the objectives of a problem, which are transcribed into attributes and structured in a hierarchical model, analyzing qualitative and quantitative data through ordinal and cardinal entries, respectively. As a case study, a decision analysis concerning the defense strategies against anti-Remotely Piloted Aircraft Systems (RPAS) strategies for the Brazilian Navy is carried out. Using the technique of the causal maps approach based on Strategic Options Development and Analysis (SODA) methodology, the problematic situation is structured for numerical implementation, demonstrating the performance of objectives and elements of a hierarchical structure. As a result, rankings concerning objectives and anti-RPAS technologies, based on the treatment of subjective information, are presented. In the end, the main contribution of the study and its limitations are discussed, along with the conclusions and some proposals for future studies. Full article

Credit card transactions may contain some categorical attributes with large domains, involving up to hundreds of possible values, also known as high-cardinality attributes. The inclusion of such attributes makes analysis harder, due to results with poorer generalization and higher resource usage. A common practice is, therefore, to ignore such attributes, removing them, albeit wasting the information they provided. Contrariwise, this paper reports our findings on the positive impacts of using high-cardinality attributes on credit card fraud detection. Thus, we present a new algorithm for domain reduction that preserves the fraud-detection capabilities. Experiments applying a deep feedforward neural network on real datasets from a major Brazilian financial institution have shown that, when measured by the F-1 metric, the inclusion of such attributes does improve fraud-detection quality. As a main contribution, this proposed algorithm was able to reduce attribute cardinality, improving the training times of a model while preserving its predictive capabilities. Full article

For continuous numerical data sets, neighborhood rough sets-based attribute reduction is an important step for improving classification performance. However, most of the traditional reduction algorithms can only handle finite sets, and yield low accuracy and high cardinality. In this paper, a novel attribute reduction method using Lebesgue and entropy measures in neighborhood rough sets is proposed, which has the ability of dealing with continuous numerical data whilst maintaining the original classification information. First, Fisher score method is employed to eliminate irrelevant attributes to significantly reduce computation complexity for high-dimensional data sets. Then, Lebesgue measure is introduced into neighborhood rough sets to investigate uncertainty measure. In order to analyze the uncertainty and noisy of neighborhood decision systems well, based on Lebesgue and entropy measures, some neighborhood entropy-based uncertainty measures are presented, and by combining algebra view with information view in neighborhood rough sets, a neighborhood roughness joint entropy is developed in neighborhood decision systems. Moreover, some of their properties are derived and the relationships are established, which help to understand the essence of knowledge and the uncertainty of neighborhood decision systems. Finally, a heuristic attribute reduction algorithm is designed to improve the classification performance of large-scale complex data. The experimental results under an instance and several public data sets show that the proposed method is very effective for selecting the most relevant attributes with high classification accuracy. Full article

The Hedonic Pricing Method is one of the principal assessment methods for evaluating services and resources not normally exchanged on the market. However, the method is often unable to account for the great variety of qualities in an urban context and faces scarce and heterogeneous market data. This paper presents a model for the valuation of benefits generated by environmental and urban improvement investments adopting a mixed hedonic-multi-attribute procedure for modeling a value function of urban real estate values. The peculiarity of the model is that the independent variables are aggregated indicators, which synthetize more detailed characteristics. Using the expertise of real estate agents, all relevant variables influencing real estate values were weighted and synthetized in a set of cardinal indicators. Next, market prices were used to calibrate a hedonic function that transforms the cardinal indicators into real estate values. The valuation model was integrated into a GIS for mapping the housing value, and its variation induced by urban investment. The proposed model pointed out plausible and robust results, in particular, the possibility to use any available information, such as location, position, technical and economic characteristics of buildings, and organize it in a flexible and transparent way, and to keep evident the role of each characteristic through the hierarchical structure of the model. The model was applied to the real estate market of Venice to test the effects of the MOSE project (Electromechanical Experimental Module) for the protection of Venice from high tides. The results of the application showed a relevant increase in real estate values in the center of Venice, especially related to property in ground floor units, of about 1.4 billion €. Full article

Introduction: Bronchial anthracofibrosis (BAF), confirmed bronchoscopically, is characterised by bluish-black mucosal pigmentation and distortion/narrowing of the bronchus. We investigated the occurrence of BAF in respiratory symptomatics with biomass fuel smoke exposure and evaluated its clinico-radiological attributes and impact on functional status. Material and methods: Of the eighty subjects evaluated, 60 consented for fiberoptic bronchoscopy (FOB). All 60 subjects also underwent chest radiography, high resolution computed tomography (HRCT) of the thorax, spirometry with reversibility testing and six-minute-walk test. Information regarding cardinal respiratory symptoms and duration of biomass fuel smoke exposure was documented. FOB evaluation revealed that 24 patients had BAF (Group 1), 17 had bronchial anthracosis (Group 2) and 19 had normal appearance (Group 3). Results: Group 1 patients had significantly higher biomass fuel smoke exposure (p < 0.0001) and lower walk distance (p = 0.003) with greater desaturation. On HRCT, segmental collapse and consolidation were significantly higher in Group 1 while fibrotic lesions were the predominantly seen in Groups 2 and 3. A significant inverse correlation in Group 1 was seen between exposure index, six-minute-walk distance and spirometric parameters. In Group 1, the right middle lobe (RML) bronchus was most commonly involved (15/24 [62.5%]). In Group 2, RML and left upper lobe bronchi were affected in 8/17 (47.1%) patients each. Conclusions: All patients in our study were females. Those with BAF had poorer functional status as compared to those with anthracosis only. On imaging, multifocal bronchial narrowing was specific to BAF.
Full article