SynBA: A contextualized Synonim-Based adversarial Attack for text classification

With the advent of high-performance computing devices, deep neural networks have gained a lot of popularity in solving many Natural Language Processing tasks. However, they are also vulnerable to adversarial attacks, which are able to modify the input text in order to mislead the target model. Adversarial attacks are a serious threat to the security of deep neural networks, and they can be used to craft adversarial examples that steer the model towards a wrong decision. In this dissertation, we propose SynBA, a novel contextualized synonym-based adversarial attack for text classification. SynBA is based on the idea of replacing words in the input text with their synonyms, which are selected according to the context of the sentence. We show that SynBA successfully generates adversarial examples that are able to fool the target model with a high success rate. We demonstrate three advantages of this proposed approach: (1) effective - it outperforms state-of-the-art attacks by semantic similarity and perturbation rate, (2) utility-preserving - it preserves semantic content, grammaticality, and correct types classified by humans, and (3) efficient - it performs attacks faster than other methods.

Pre-processing for noise detection in gene expression classification data

Due to the imprecise nature of biological experiments, biological data is often characterized by the presence of redundant and noisy data. This may be due to errors that occurred during data collection, such as contaminations in laboratorial samples. It is the case of gene expression data, where the equipments and tools currently used frequently produce noisy biological data. Machine Learning algorithms have been successfully used in gene expression data analysis. Although many Machine Learning algorithms can deal with noise, detecting and removing noisy instances from the training data set can help the induction of the target hypothesis. This paper evaluates the use of distance-based pre-processing techniques for noise detection in gene expression data classification problems. This evaluation analyzes the effectiveness of the techniques investigated in removing noisy data, measured by the accuracy obtained by different Machine Learning classifiers over the pre-processed data.

An exploratory analysis of relationships between socioeconomic, land use, activity participation variables and travel patterns

This paper aims to find relations between the socioeconomic characteristics, activity participation, land use patterns and travel behavior of the residents in the Sao Paulo Metropolitan Area (SPMA) by using Exploratory Multivariate Data Analysis (EMDA) techniques. The variables influencing travel pattern choices are investigated using: (a) Cluster Analysis (CA), grouping and characterizing the Traffic Zones (17), proposing the independent variable called Origin Cluster and, (b) Decision Tree (DT) to find a priori unknown relations among socioeconomic characteristics, land use attributes of the origin TZ and destination choices. The analysis was based on the origin-destination home-interview survey carried out in SPMA in 1997. The DT application revealed the variables of greatest influence on the travel pattern choice. The most important independent variable considered by DT is car ownership, followed by the Use of Transportation ""credits"" for Transit tariff, and, finally, activity participation variables and Origin Cluster. With these results, it was possible to analyze the influence of a family income, car ownership, position of the individual in the family, use of transportation ""credits"" for transit tariff (mainly for travel mode sequence choice), activities participation (activity sequence choice) and Origin Cluster (destination/travel distance choice). (c) 2010 Elsevier Ltd. All rights reserved.

Spatial portability of numerical models of leaf wetness duration based on empirical approaches

Leaf wetness duration (LWD) models based on empirical approaches offer practical advantages over physically based models in agricultural applications, but their spatial portability is questionable because they may be biased to the climatic conditions under which they were developed. In our study, spatial portability of three LWD models with empirical characteristics - a RH threshold model, a decision tree model with wind speed correction, and a fuzzy logic model - was evaluated using weather data collected in Brazil, Canada, Costa Rica, Italy and the USA. The fuzzy logic model was more accurate than the other models in estimating LWD measured by painted leaf wetness sensors. The fraction of correct estimates for the fuzzy logic model was greater (0.87) than for the other models (0.85-0.86) across 28 sites where painted sensors were installed, and the degree of agreement k statistic between the model and painted sensors was greater for the fuzzy logic model (0.71) than that for the other models (0.64-0.66). Values of the k statistic for the fuzzy logic model were also less variable across sites than those of the other models. When model estimates were compared with measurements from unpainted leaf wetness sensors, the fuzzy logic model had less mean absolute error (2.5 h day(-1)) than other models (2.6-2.7 h day(-1)) after the model was calibrated for the unpainted sensors. The results suggest that the fuzzy logic model has greater spatial portability than the other models evaluated and merits further validation in comparison with physical models under a wider range of climate conditions. (C) 2010 Elsevier B.V. All rights reserved.

Disaggregation of polygons of surficial geology and soil maps using spatial modelling and legacy data

Examples from the Murray-Darling basin in Australia are used to illustrate different methods of disaggregation of reconnaissance-scale maps. One approach for disaggregation revolves around the de-convolution of the soil-landscape paradigm elaborated during a soil survey. The descriptions of soil ma units and block diagrams in a soil survey report detail soil-landscape relationships or soil toposequences that can be used to disaggregate map units into component landscape elements. Toposequences can be visualised on a computer by combining soil maps with digital elevation data. Expert knowledge or statistics can be used to implement the disaggregation. Use of a restructuring element and k-means clustering are illustrated. Another approach to disaggregation uses training areas to develop rules to extrapolate detailed mapping into other, larger areas where detailed mapping is unavailable. A two-level decision tree example is presented. At one level, the decision tree method is used to capture mapping rules from the training area; at another level, it is used to define the domain over which those rules can be extrapolated. (C) 2001 Elsevier Science B.V. All rights reserved.

Hyperplane navigation: A method to set individual scores in fMRI group datasets

Recent studies have demonstrated that spatial patterns of fMRI BOLD activity distribution over the brain may be used to classify different groups or mental states. These studies are based on the application of advanced pattern recognition approaches and multivariate statistical classifiers. Most published articles in this field are focused on improving the accuracy rates and many approaches have been proposed to accomplish this task. Nevertheless, a point inherent to most machine learning methods (and still relatively unexplored in neuroimaging) is how the discriminative information can be used to characterize groups and their differences. In this work, we introduce the Maximum Uncertainty Linear Discrimination Analysis (MLDA) and show how it can be applied to infer groups` patterns by discriminant hyperplane navigation. In addition, we show that it naturally defines a behavioral score, i.e., an index quantifying the distance between the states of a subject from predefined groups. We validate and illustrate this approach using a motor block design fMRI experiment data with 35 subjects. (C) 2008 Elsevier Inc. All rights reserved.

Cost-effectiveness analysis of routine rotavirus vaccination in Brazil

Objective. The objective of this study was to conduct a cost-effectiveness analysis of a universal rotavirus vaccination program among children : 5 years of age in Brazil. Methods. Considering a hypothetical annual cohort of approximately 3 300 000 newborns followed over 5 years, a decision-tree model was constructed to examine the possible clinical and economic effects of rotavirus infection with and without routine vaccination of children. Probabilities and unit costs were derived from published research and national administrative data. The impact of different estimates for key parameters was studied using sensitivity analysis. The analysis was conducted from both healthcare system and societal perspectives. Results. The vaccination program was estimated to prevent approximately 1735 351 (54%) of the 3 210 361 cases of rotavirus gastroenteritis and 703 (75%) of 933 rotavirus-associated deaths during the 5-year period. At a vaccine price of 18.6 Brazilian reais (R$) per dose, this program would cost R$121 673 966 and would save R$38 536 514 in direct costs to the public healthcare system and R$71 778 377 in direct and indirect costs to society. The program was estimated to cost R$1 028 and R$1 713 per life-years saved (LYS)from the societal and healthcare system perspectives, respectively. Conclusions. Universal rotavirus vaccination was a cost-effective strategy for both perspectives. However, these findings are highly sensitive to diarrhea incidence rate, proportion of severe cases, vaccine coverage, and vaccine price.

Integrating high and moderate spatial resolution image data to estimate forest age structure

The collection of spatial information to quantify changes to the state and condition of the environment is a fundamental component of conservation or sustainable utilization of tropical and subtropical forests, Age is an important structural attribute of old-growth forests influencing biological diversity in Australia eucalypt forests. Aerial photograph interpretation has traditionally been used for mapping the age and structure of forest stands. However this method is subjective and is not able to accurately capture fine to landscape scale variation necessary for ecological studies. Identification and mapping of fine to landscape scale vegetative structural attributes will allow the compilation of information associated with Montreal Process indicators lb and ld, which seek to determine linkages between age structure and the diversity and abundance of forest fauna populations. This project integrated measurements of structural attributes derived from a canopy-height elevation model with results from a geometrical-optical/spectral mixture analysis model to map forest age structure at a landscape scale. The availability of multiple-scale data allows the transfer of high-resolution attributes to landscape scale monitoring. Multispectral image data were obtained from a DMSV (Digital Multi-Spectral Video) sensor over St Mary's State Forest in Southeast Queensland, Australia. Local scene variance levels for different forest tapes calculated from the DMSV data were used to optimize the tree density and canopy size output in a geometric-optical model applied to a Landsat Thematic Mapper (TU) data set. Airborne laser scanner data obtained over the project area were used to calibrate a digital filter to extract tree heights from a digital elevation model that was derived from scanned colour stereopairs. The modelled estimates of tree height, crown size, and tree density were used to produce a decision-tree classification of forest successional stage at a landscape scale. The results obtained (72% accuracy), were limited in validation, but demonstrate potential for using the multi-scale methodology to provide spatial information for forestry policy objectives (ie., monitoring forest age structure).

Maximum Likelihood Estimation of Mixture Densities for Binned and Truncated Multivariate Data

Binning and truncation of data are common in data analysis and machine learning. This paper addresses the problem of fitting mixture densities to multivariate binned and truncated data. The EM approach proposed by McLachlan and Jones (Biometrics, 44: 2, 571-578, 1988) for the univariate case is generalized to multivariate measurements. The multivariate solution requires the evaluation of multidimensional integrals over each bin at each iteration of the EM procedure. Naive implementation of the procedure can lead to computationally inefficient results. To reduce the computational cost a number of straightforward numerical techniques are proposed. Results on simulated data indicate that the proposed methods can achieve significant computational gains with no loss in the accuracy of the final parameter estimates. Furthermore, experimental results suggest that with a sufficient number of bins and data points it is possible to estimate the true underlying density almost as well as if the data were not binned. The paper concludes with a brief description of an application of this approach to diagnosis of iron deficiency anemia, in the context of binned and truncated bivariate measurements of volume and hemoglobin concentration from an individual's red blood cells.

Quantitative evaluation of altered hepatic spaces and membrane transport in fibrotic rat liver

Four animal models were used to quantitatively evaluate hepatic alterations in this study: (1) a carbon tetrachloride control group (phenobarbital treatment only), (2) a CCl4-treated group (phenobarbital with CCl4 treatment), (3) an alcohol-treated group (liquid diet with alcohol treatment), and (4) a pair-fed alcohol control group (liquid diet only). At the end of induction, single-pass perfused livers were used to conduct multiple indicator dilution (MID) studies. Hepatic spaces (vascular space, extravascular albumin space, extravascular sucrose space, and cellular distribution volume) and water hepatocyte permeability/surface area product were estimated from nonlinear regression of outflow concentration versus time profile data. The hepatic extraction ratio of H-3-taurocholate was determined by the nonparametric moments method. Livers were then dissected for histopathologic analyses (e.g., fibrosis index, number of fenestrae). In these 4 models, CCl4-treated rats were found to have the smallest vascular space, extravascular albumin space, H-3-taurocholate extraction, and water hepatocyte permeability/surface area product but the largest extravascular sucrose space and cellular distribution volume. In addition, a linear relationship was found to exist between histopathologic analyses (fibrosis index or number of fenestrae) and hepatic spaces. The hepatic extraction ratio of H-3-taurocholate and water hepatocyte permeability/surface area product also correlated to the severity of fibrosis as defined by the fibrosis index. In conclusion, the multiple indicator dilution data obtained from the in situ perfused rat liver can be directly related to histopathologic analyses.

Computer-aided recognition of dental implants in X-ray images

Dental implant recognition in patients without available records is a time-consuming and not straightforward task. The traditional method is a complete user-dependent process, where the expert compares a 2D X-ray image of the dental implant with a generic database. Due to the high number of implants available and the similarity between them, automatic/semi-automatic frameworks to aide implant model detection are essential. In this study, a novel computer-aided framework for dental implant recognition is suggested. The proposed method relies on image processing concepts, namely: (i) a segmentation strategy for semi-automatic implant delineation; and (ii) a machine learning approach for implant model recognition. Although the segmentation technique is the main focus of the current study, preliminary details of the machine learning approach are also reported. Two different scenarios are used to validate the framework: (1) comparison of the semi-automatic contours against implant’s manual contours of 125 X-ray images; and (2) classification of 11 known implants using a large reference database of 601 implants. Regarding experiment 1, 0.97±0.01, 2.24±0.85 pixels and 11.12±6 pixels of dice metric, mean absolute distance and Hausdorff distance were obtained, respectively. In experiment 2, 91% of the implants were successfully recognized while reducing the reference database to 5% of its original size. Overall, the segmentation technique achieved accurate implant contours. Although the preliminary classification results prove the concept of the current work, more features and an extended database should be used in a future work.