Relating instance hardness to classification performance in a dataset: a visual approach

Machine Learning - Machine Learning studies often involve a series of computational experiments in which the predictive performance of multiple models are compared across one or more datasets. The...     

Diagnosis of lung nodule using Moran’s index and Geary’s coefficient in computerized tomography images

This paper analyzes the application of Moran’s index and Geary’s coefficient to the characterization of lung nodules as malignant or benign in computerized tomography images. The characterization method is based on a process that verifies which combination of measures, from the proposed measures, has been best able to discriminate between the benign and malignant nodules using stepwise discriminant analysis. Then, a linear discriminant analysis procedure was performed using the selected features to evaluate the ability of these in predicting the classification for each nodule. In order to verify this application we also describe tests that were carried out using a sample of 36 nodules: 29 benign and 7 malignant. A leave-one-out procedure was used to provide a less biased estimate of the linear discriminator’s performance. The two analyzed functions and its combinations have provided above 90% of accuracy and a value area under receiver operation characteristic (ROC) curve above 0.85, that indicates a promising potential to be used as nodules signature measures. The preliminary results of this approach are very encouraging in characterizing nodules using the two functions presented.

Improving the performance of fuzzy rules-based forecasters through application of FCM algorithm

Prediction models based on artificial intelligence techniques have been widely used in Time Series Forecasting in several areas. They are often fuzzy models or neural networks. This paper describes the development of neural and fuzzy models for forecasting time series of practical examples, and shows the comparisons of results between models, including the results of statistical modeling. The use of data clustering algorithms like Fuzzy C-Means is considered in fuzzy models.     

Immersive and interactive virtual reality applications based on 3D web browsers

This study explores the possibility of effectively using web-standard technologies (i.e., HTML5, JavaScript, WebGL, and WebRTC) to deploy full immersive and interactive virtual reality applications. These applications are based on computer clusters and run in multi-projection environments, such as CAVEs, Panoramas and Power Walls. Until recently, these applications were build using tailored solutions, such low-level libraries to distribute data. We discuss the modern-day web technology which allows these applications meet a multi-platform requirement. This paper also evaluates the communication and synchronization requirements of these applications that are traditionally the main bottleneck. As a proof-of-concept to show the feasibility of our study, we devised and implemented an immersive and interactive virtual reality application employing only web technologies. Our proof-of-concept runs on a miniCAVE environment with three displays and a 6-node cluster.     

A backstepping controller for path‐tracking of an underactuated autonomous airship

In this paper we propose a nonlinear control approach for the path‐tracking of an autonomous underactuated airship. A backstepping controller is designed from the airship nonlinear dynamic model including wind disturbances, and further enhanced to consider actuators saturation. Control implementation issues related to airship underactuation are also addressed, namely control allocation and an attitude reference shaping to obtain a faster error correction with smoother input requests. The results obtained demonstrate the capacity of an underactuated unmanned airship to execute a realistic mission including vertical take‐off and landing, stabilization and path‐tracking, in the presence of wind disturbances, with a single robust control law. Copyright © 2008 John Wiley & Sons, Ltd.     

Modeling culture in intelligent virtual agents

This work addresses the challenge of creating virtual agents that are able to portray culturally appropriate behavior when interacting with other agents or humans. Because culture influences how people perceive their social reality it is important to have agent models that explicitly consider social elements, such as existing relational factors. We addressed this necessity by integrating culture into a novel model for simulating human social behavior. With this model, we operationalized a particular dimension of culture—individualism versus collectivism—within the context of an interactive narrative scenario that is part of an agent-based tool for intercultural training. Using this scenario we conducted a cross-cultural study in which participants from a collectivistic country (Portugal) were compared with participants from an individualistic country (the Netherlands) in the way they perceived and interacted with agents whose behavior was either individualistic or collectivistic, according to the configuration of the proposed model. In the obtained results, Portuguese subjects rated the collectivistic agents more positively than the Dutch but both countries had a similarly positive opinion about the individualistic agents. This experiment sheds new light on how people from different countries differ when assessing the social appropriateness of virtual agents, while also raising new research questions on this matter.     

Processing and thermomechanical evaluation of fibre-reinforced alumina filters

Impregnation of polymeric foams with ceramic suspensions has been widely employed in industry to fabricate ceramic filters of various shapes and controlled pore size at a reduced processing cost. Ceramic filters find application in cast metal industry to remove the undesired impurities from the melt, leading to products of higher quality. This paper reports a complete study on the fabrication of fibre-reinforced alumina filters. Rheological measurements of ceramic suspensions showed that the slip adherence on polymer substrate was largely improved when thickening agent was incorporated into the compositions, as a result of the increase in pseudoplasticity and in viscosity. Thermomechanical evaluation of the filters produced with fibre addition revealed that the fibre reinforcement improved the mechanical performance and reduced the damage by applied thermal stresses. Strengthening and toughening of the ceramic matrix has been explained based on the fibre properties, fibre-matrix interface strength and thermal expansion mismatch that may occur in mixed systems.     

Mass Balance in Eulerian-Lagrangian Transport Simulations in Estuaries

This paper investigates the generation of flow mass errors in finite-element shallow water models and the effect of these errors in the mass conservation of Eulerian-Lagrangian transport simulations. Flow mass errors are shown to be similar for several primitive and wave equation formulations. These errors occur primarily in areas of steep bathymetric gradients and near complex boundaries. Forcing Eulerian-Lagrangian transport simulations with nonconservative flow fields generates important mass imbalances, which can be mitigated by refining the flow grid. Comparatively, refining the transport grid only reduces marginally the mass errors.     

An international study on sleep disorders in the general population: methodological aspects of the use of the Sleep-EVAL system

The comparability among epidemiological surveys of sleep disorders has been encumbered because of the array of methodologies used from study to study. The present international initiative addresses this limitation. Many such studies using the exact same methodology are being completed in six European countries (France, the United Kingdom, Germany, Italy, Portugal, and Spain), two Canadian cities (metropolitan areas of Montreal and Toronto), New York State, and the city of San Francisco. These surveys have been undertaken with the aim of documenting the prevalence of sleep disorders in the general population according to criteria of the Diagnostic and Statistical Manual of Mental Disorders, 4th edition (DSM-IV) and the International Classification of Sleep Disorders (ICSD-90). Data are gathered over the telephone by lay interviewers using the Sleep-EVAL expert system. This paper describes the methodology involved in the realization of these studies. Sample design and selection procedures are discussed.     

Parametric Analysis of the Stability of Degraded Railroad Platforms

The current study is developed based on one of the types of subgrade rupture risk suggested by Selig and Waters （1994）. It aims to evaluate subgrade stability railroad, which consists of the slope stability analysis of a railway yard embankment subjected to a wagon load type gondola parked on this track. This proposed analysis was taken into consideration because there are Brazilian railroads in high deterioration level. In some of these lines the tracks are submitted to increasing amount of load every year. The adopted model slope stability to the studied railroad embankments considers the rupture on circular line. It was applied the Geoslope-Slope/W software, version 6, to the evaluation of the platform-slope system. Several situations are adopted to reach the minimum safety slope, permitting to analyze the platform stability to keep railroad traffic under adequate safety level.