Optimized approach to decision fusion of heterogeneous data for breast cancer diagnosis.

As more diagnostic testing options become available to physicians, it becomes more difficult to combine various types of medical information together in order to optimize the overall diagnosis. To improve diagnostic performance, here we introduce an approach to optimize a decision-fusion technique to combine heterogeneous information, such as from different modalities, feature categories, or institutions. For classifier comparison we used two performance metrics: The receiving operator characteristic (ROC) area under the curve [area under the ROC curve (AUC)] and the normalized partial area under the curve (pAUC). This study used four classifiers: Linear discriminant analysis (LDA), artificial neural network (ANN), and two variants of our decision-fusion technique, AUC-optimized (DF-A) and pAUC-optimized (DF-P) decision fusion. We applied each of these classifiers with 100-fold cross-validation to two heterogeneous breast cancer data sets: One of mass lesion features and a much more challenging one of microcalcification lesion features. For the calcification data set, DF-A outperformed the other classifiers in terms of AUC (p < 0.02) and achieved AUC=0.85 +/- 0.01. The DF-P surpassed the other classifiers in terms of pAUC (p < 0.01) and reached pAUC=0.38 +/- 0.02. For the mass data set, DF-A outperformed both the ANN and the LDA (p < 0.04) and achieved AUC=0.94 +/- 0.01. Although for this data set there were no statistically significant differences among the classifiers' pAUC values (pAUC=0.57 +/- 0.07 to 0.67 +/- 0.05, p > 0.10), the DF-P did significantly improve specificity versus the LDA at both 98% and 100% sensitivity (p < 0.04). In conclusion, decision fusion directly optimized clinically significant performance measures, such as AUC and pAUC, and sometimes outperformed two well-known machine-learning techniques when applied to two different breast cancer data sets.

The ocean sampling day consortium.

Ocean Sampling Day was initiated by the EU-funded Micro B3 (Marine Microbial Biodiversity, Bioinformatics, Biotechnology) project to obtain a snapshot of the marine microbial biodiversity and function of the world's oceans. It is a simultaneous global mega-sequencing campaign aiming to generate the largest standardized microbial data set in a single day. This will be achievable only through the coordinated efforts of an Ocean Sampling Day Consortium, supportive partnerships and networks between sites. This commentary outlines the establishment, function and aims of the Consortium and describes our vision for a sustainable study of marine microbial communities and their embedded functional traits.

Response Surface Modeling and Optimisation for Reliable Electronic Products

The aim of integrating computational mechanics (FEA and CFD) and optimization tools is to speed up dramatically the design process in different application areas concerning reliability in electronic packaging. Design engineers in the electronics manufacturing sector may use these tools to predict key design parameters and configurations (i.e. material properties, product dimensions, design at PCB level. etc) that will guarantee the required product performance. In this paper a modeling strategy coupling computational mechanics techniques with numerical optimization is presented and demonstrated with two problems. The integrated modeling framework is obtained by coupling the multi-physics analysis tool PHYSICA - with the numerical optimization package - Visua/DOC into a fuJly automated design tool for applications in electronic packaging. Thermo-mechanical simulations of solder creep deformations are presented to predict flip-chip reliability and life-time under thermal cycling. Also a thermal management design based on multi-physics analysis with coupled thermal-flow-stress modeling is discussed. The Response Surface Modeling Approach in conjunction with Design of Experiments statistical tools is demonstrated and used subsequently by the numerical optimization techniques as a part of this modeling framework. Predictions for reliable electronic assemblies are achieved in an efficient and systematic manner.

GIS on tourism planning: preventing the impacts caused by the developing tourism activity in a specific site

The environment is one of the greatest concerns of humankind. Nowadays, the activities which improve or destroy it must be assessed and controlled by efficient means which should permit the control of environmental impact caused by the development of these activities. This document presents an information system implementation, as a Decision Support system, allowing the Decision Maker to evaluate, foresee and control the future environmental impact of Tourism through consultation, the management and the presentation of decision schemes based on defined measures of a regional tourism planning.

Public transport travel planning application

Here it is presented an application that plans out travel on public transports and that chooses the best ones, according to preference criteria provided by the user. These criteria are: the time spent on the travel, the price of the tickets and the quality of the transports. The application combines different means of transport. Algorithms and heuristics were developed to draw up transport plans and to choose the best ones. The best plans are determined using the multi-attributes decision techniques. The application uses a database that was developed in a Relational Database Management System. To draw the database at the conceptual and the applicational level, it was used one of the models based on the object, the Entity-Relationship Mode

SGBD de alta escalabilidade com suporte a dados georreferenciados

Trabalho Final de Mestrado para obtenção do grau de Mestre em Engenharia Informática e de Computadores

Comuns: An Open-Data Provider, Explorer and Analytic Toolbox Based on FOSS

Contém resumo

Generalized Dasymetric Mapping Algorithm for Accessing Land-Use Change

Contém resumo

On Implementing Joins, Aggregates and Universal Quantifier in Temporal Databases using SQL Standards

A feasible way of implementing a temporal database is by mapping temporal data model onto a conventional data model followed by a commercial database management system. Even though extensions were proposed to standard SQL for supporting temporal databases, such proposals have not yet come across standardization processes. This paper attempts to implement database operators such as aggregates and universal quantifier for temporal databases, implemented on top of relational database systems, using currently available SQL standards.

Ruteador inteligente y dinámico basado en clasificación del tráfico en tres niveles

This project describes a Web Geographic Information System (WebGIS) built on an Open Source geographic structure lice MapServer (Minnesota University) and PostgreSQL/PostGIS (object relational database management system). The WebGIS is a web site to route ways in streets net of a part of Sao Paulo city (Brazil). The system traces the route based in a best way algorithm looking for better streets traffic conditions

Sistema de información geográfica para web con informaciones espaciales (geográficas) de output y input para expediciones

This project is a Web Geographic Information System built on an Open Source geographic structure like MapServer (Minnesota University) and PostgreSQL/PostGIS (object relational database management system). The study case is a web site for expeditions in a specific Brazilian region

Evaluación de la gestión de residuos derivados del proceso de impresión en Datapoint de Colombia S.A.S, y propuesta de mejora

Este trabajo se centra en el análisis de las actividades desarrolladas en torno a los servicios de procesos de impresión que ofrece la organización DATAPOINT de Colombia SAS para identificar los puntos críticos en la gestión de los residuos de impresión y las decisiones tomadas por parte de los involucrados durante todo el proceso (proveedores, clientes y la empresa), con el fin de revisar medidas y estrategias que permitan fortalecer la gestión integral de residuos de impresión a partir de una revisión y comparación de las mejores prácticas planteadas por los actores del sector. También se efectuaron recomendaciones con acciones de mejora que se podrían desarrollar con el fin de mitigar el impacto ambiental generado por estos residuos. Con la finalidad de cumplir con lo planteado se realizó inicialmente un estudio sobre la organización, sus clientes y proveedores para entender de manera integral la cadena de valor en torno a los tóner y su gestión inversa, (explicar) al igual que el entorno normativo tanto de manera nacional como internacional. Posteriormente, se identificaron los puntos de mejora comparando lo planteado por el proveedor versus lo ejecutado por los involucrados en el proceso, labor se realizó en campo con los clientes para entender la situación actual, sus necesidades y en que basan la toma de decisiones relacionada con el manejo de los residuos de impresión. Finalmente se listaran una serie de acciones de mejora y recomendaciones las cuales pueden ser incorporadas a los procesos críticos de DATAPOINT.

Preventing drug related morbidity: a process for facilitating changes in practice

Aim: To describe how quantitative data obtained from applying a series of indicators for preventable drug related morbidity (PDRM) in the electronic patient record in English general practice can be used to facilitate changes aimed at helping to improve medicines management. Design: A multidisciplinary discussion forum held at each practice facilitated by a clinical researcher. Subjects and setting: Eight English general practices. Outcome measures: Issues discussed at the multidisciplinary discussion forum and ideas generated by practices for tackling these issues. Progress made by practices after 1, 3, and 6 months. Results: A number of clinical issues were raised by the practices and ideas for moving them forward were discussed. The issues that were easiest and most straightforward to deal with (for example, reviewing specific patient groups) were quickly addressed in most instances. Practices were less likely to have taken steps towards addressing issues at a systems level. Conclusions: Data generated from applying PDRM indicators can be used to facilitate practice-wide discussion on medicines management. Different practices place different priority levels on the issues they wish to pursue. Individual practice "ownership'' of these, together with having a central committed figure at the practice, is key to the success of the process.