Alcione de Paiva Oliveira

Multi-objective Variable Neighborhood Search Algorithms for a Single Machine Scheduling Problem with Distinct due Windows

In this paper, we compare three multi-objective algorithms based on Variable Neighborhood Search (VNS) heuristic. The algorithms are applied to solve the single machine scheduling problem with sequence dependent setup times and distinct due windows. In this problem, we consider minimizing the total weighted earliness/tardiness and the total flowtime criteria. We introduce two intensification procedures to improve a multi-objective VNS (MOVNS) algorithm proposed in the literature. The performance of the algorithms is tested on a set of medium and larger instances of the problem. The computational results show that the proposed algorithms outperform the original MOVNS algorithm in terms of solution quality. A statistical analysis is conducted in order to analyze the performance of the proposed methods.

An Infrastructure Oriented for Cataloging Services and Reuse of Analysis Patterns

Patterns have been employed as a mechanism for reuse in several phases of software development. Analysis patterns consist of artifacts for reuse during the requirements analysis and conceptual modeling. However, they are generally, documented in a textual manner which is not precise to be treated by a computer, thus limiting the dissemination and a wider reuse. Within the geo-processing area, Spatial Data Infrastructures (SDI) has been used quite effectively as an instrument for the reuse of geospatial data and services. Based on the development of SDIs, this article proposes an Analysis Patterns Reuse Infrastructure (APRI) comprising web services and a metadata representation for the specification of analysis patterns, in order to support the cataloging and reusing of analysis patterns.

NICeSim: An open-source simulator based on machine learning techniques to support medical research on prenatal and perinatal care decision making

OBJECTIVE This paper describes NICeSim, an open-source simulator that uses machine learning (ML) techniques to aid health professionals to better understand the treatment and prognosis of premature newborns. METHODS The application was developed and tested using data collected in a Brazilian hospital. The available data were used to feed an ML pipeline that was designed to create a simulator capable of predicting the outcome (death probability) for newborns admitted to neonatal intensive care units. However, unlike previous scoring systems, our computational tool is not intended to be used at the patients bedside, although it is possible. Our primary goal is to deliver a computational system to aid medical research in understanding the correlation of key variables with the studied outcome so that new standards can be established for future clinical decisions. In the implemented simulation environment, the values of key attributes can be changed using a user-friendly interface, where the impact of each change on the outcome is immediately reported, allowing a quantitative analysis, in addition to a qualitative investigation, and delivering a totally interactive computational tool that facilitates hypothesis construction and testing. RESULTS Our statistical experiments showed that the resulting model for death prediction could achieve an accuracy of 86.7% and an area under the receiver operating characteristic curve of 0.84 for the positive class. Using this model, three physicians and a neonatal nutritionist performed simulations with key variables correlated with chance of death. The results indicated important tendencies for the effect of each variable and the combination of variables on prognosis. We could also observe values of gestational age and birth weight for which a low Apgar score and the occurrence of respiratory distress syndrome (RDS) could be less or more severe. For instance, we have noticed that for a newborn with 2000 g or more the occurrence of RDS is far less problematic than for neonates weighing less. CONCLUSIONS The significant accuracy demonstrated by our predictive model shows that NICeSim might be used for hypothesis testing to minimize in vivo experiments. We observed that the model delivers predictions that are in very good agreement with the literature, demonstrating that NICeSim might be an important tool for supporting decision making in medical practice. Other very important characteristics of NICeSim are its flexibility and dynamism. NICeSim is flexible because it allows the inclusion and deletion of variables according to the requirements of a particular study. It is also dynamic because it trains a just-in-time model. Therefore, the system is improved as data from new patients become available. Finally, NICeSim can be extended in a cooperative manner because it is an open-source system.

Linfócitos T CD4+CD25+ e a regulação do sistema imunológico: perspectivas para o entendimento fisiopatológico da sepse

The systemic inflammatory response represents the core pathogenic event of sepsis, underlying clinical manifestations and laboratory findings in patients. Numerous studies have shown that CD4+CD25+ T lymphocytes, also known as regulatory T lymphocytes (Treg), participate in the development of sepsis due to their ability to suppress the immune response. The present article discusses the role of Treg lymphocytes in sepsis based on a specific search strategy (Latin American and Caribbean Health Sciences / Literatura Latino-americana e do Caribe em Ciencias da Saude - LILACS, PubMed, and Scientific Electronic Library Online - SciELO) focusing on two main topics: the participation of Treg cells in inflammation and immunity as well as perspectives in the computational physiological investigation of sepsis.

As redes neurais artificiais e o ensino da medicina

The transformations that medical practice has undergone in recent years - especially with the incorporation of new information technologies - point to the need to broaden discussions on the teaching-learning process in medical education. The use of new computer technologies in medical education has shown many advantages in the process of acquiring skills in problem solving, which encourages creativity, critical thinking, curiosity and scientific spirit. In this context, it is important to highlight artificial neural networks (ANN) - computer systems with a mathematical structure inspired by the human brain - which proved to be useful in the evaluation process and the acquisition of knowledge among medical students. The purpose of this communication is to review aspects of the application of ANN in medical education.

Selection of Software Development Good Practices in Micro and Small Enterprises: An Approach Using Knowledge-Based Systems

Currently, companies should turn their attention to the increasing market competition. The quality of their products is directly related to the organizational processes that should be well defined and adopted. Regarding software, it is important that the choice of a development method is aimed at matching organization needs and its production culture. The micro and small enterprises face many problems and one of the largest ones is the lack of policies that can help improving development processes. This paper presents and describes a knowledge-based system that is able to suggest a set of good practices in software development that closely match company needs and culture represented as a profile. The work exposed here is an initial step towards an automation process for the selection of good practices based on a company profile.

Pro-Inflammatory Cytokines in Sepsis: Biological Studies and Prospects From In Silico Research

Sepsis is one of the leading causes of death in intensive care units (ICUs) and is responsible for thousands of annual deaths worldwide. The pro-inflammatory cytokines are necessary for the control of infection and are the primary focus of this paper. Due to their central role in the pathogenesis of sepsis, more emphasis is needed on the use of cytokine as biomarkers. Implementation of the cytokines in the AutoSimmune for immune system simulations may improve understanding of aspects of the physiopathology of disease in humans. We present the principal aspects of the pathogenesis of the pro-inflammatory response in sepsis and the possibilities of their modulation in order to alter the course of this illness. We highlight the main pro-inflammatory cytokines that may be used as biomarkers in clinical practice. We also discuss the perspectives of sepsis in silico investigation, using the AutoSimmune computational system. Sepsis remains a true challenge in contemporary clinical practice, especially in terms of diagnosis, therapeutics, and prognosis. A greater understanding of inflammation in sepsis – especially in relation to cellular and molecular participation in the development of the morbid process – has the potentiality for the development of new investigative methods and outcome prediction, elements that may aid in offering good patient care.

DC2DP: A Dublin Core Application Profile to Design Patterns

Design patterns describe reusable solutions to existing problems in object-oriented software development. Design patterns are mostly documented in written form in books and scientific papers, which hinders processing them via computer, their diffusion, and their broader reuse. They can also be found on the internet, though documented with little detail, which makes it hard to understand and consequently reuse them. This paper presents an application profile of the Dublin Core metadata standard specific for design patterns, called DC2DP. The goal is to allow design patterns to be documented so as to provide the user with a more detailed and standardized description, besides enabling automatic processing through web services. The paper also extends an Analysis Patterns Reuse Infrastructure (APRI) by adding a design pattern repository to it, thus allowing these patterns to be cataloged and searched, which makes their discovery, study, and reuse easier.

An evolutionary algorithm with path-relinking for the parallel machine with job splitting

This paper addresses the parallel machine scheduling problem which consists in the assignment of n jobs on m identical machines with the objective of minimizing the total tardiness of the jobs using the job splitting property. In this problem is assumed that a job can be split into sub-jobs and these sub-jobs can be processed independently on parallel machines. This is an NP-hard problem and few solution methods have been proposed to solve it. In this paper, we propose a Genetic Algorithm coupled with Path Relinking intensification to obtain near-optimal solutions of the problem. To evaluate the performance of the algorithm, computational experiments are performed on a benchmark of small and large instances of the problem. Results of the experiments show that the proposed algorithm outperforms others algorithms previously proposed in the literature in terms of solution quality. The results are confirmed by a statistical analysis.

Theoretical Basis of a New Method for DNA Fragment Assembly in k-mer Graphs

The reduction of cost and running time provided by new generation sequencing technologies made possible the emergence of thousands of genome projects in the last few years. On the other hand, those technologies posed important computational challenges, pushing the advance of many research fields in computer science. Particularly, the de novo DNA fragment assembly, which is a fundamental stage in genome sequencing, is a complex problem that demands complex algorithms to solve it. Here, we provide a theoretical basis for the construction of a new method for de novo fragment assembly based on k-mer graphs. Our proposal encompasses many difficulties found in such problems using a unique procedure, in contrast with current methods that use several high-cost procedures to overcome the same issues. Furthermore, our approach is highly scalable since it allows the use of parallelism, being very suitable for solutions with graphics processing unit (GPU).