Search

Proper management of projects has become an element of vital importance for the solution to problems of society. In this context, there are two main objectives to be solved: the construction of project plans which may comply with the constraints of the problem and the optimization in terms of cost and time of those plans. To this end, all activities of project must be organized in such way that the constraints related to the precedence among them and the availability of renewable and non-renewable resources at each instant of time are met. The aim of this paper is to present an Estimation of Distribution Algorithm (EDA), which incorporates the handling of the constraints in the probabilistic model, for the construction of optimal or quasi-optimal project plans. For the validation of the algorithm, authors used both the PSPLib database repository for the development of the scheduling research and the databases of projects of the Repository for Research in Project Management, University of Infomatic Sciences. [ABSTRACT FROM AUTHOR]

One of the risks during pregnancy, with high negative impact on both pregnant and fetus is cardiovascular disease suffering. Early diagnosis and appropriate treatment of this pathology significantly reduce the risk for pregnant. The treatment of pregnant women with heart diseases is characterized by the insufficient availability of experts with knowledge of medical specialties involved, and by the presence of situations of indeterminacy, uncertainty, vagueness, and incomplete data. Hence the need to create novel computational techniques for supporting clinical decision making during the treatment of these diseases. In this paper, we suggest a new model based on Neutrosophic Cognitive Map that integrates diagnosis, treatment, and prognosis processes for supporting clinical decision making during the treatment of pregnant women with cardiovascular diseases. The model introduces a new approach to represent the map's connections, by using Triangular Neutrosophic Numbers, making it possible to quantify the truth, indeterminacy, and falsity degrees of experts' preferences. The new model aims to improve the accuracy of diagnosis and treatment of heart diseases during pregnancy; and to mitigate the lack of expertise in this area. In validation process, a data base with 1019 cases provided by Cardiovascular and Pregnancy National Service/Gynecology and Obstetrics Hospital Ramón Gonzales Coros is used, and model's results are evaluated by experts to demonstrate the efficiency of the proposed model for treating these diseases during pregnancy. [ABSTRACT FROM AUTHOR]

The growth of project management as international discipline was encouraged by the increasing of projects complexity all over the world. Despite of the effort made by the principal standards of project management, the number of failed and renegotiated projects still very high. Decision making process is one of the root causes of projects failure. During project development, decisions are made according to the evaluations performed in projects cut. In each cut, experts make, sequentially, diagnosis, decision, and prediction processes. This paper aims at creating a new model that integrate the diagnosis, decision, and prediction processes in one platform for decision making during projects development. The new model is based on Neutrosophic Cognitive Maps (NCMs) with a triangular neutrosophic number in map's connections. The suggested model deals efficiently with the uncertainty and vagueness, since it considers the truth, indeterminacy, and falsity degrees. Finally, the proposed model has been compared, in terms of efficacy, with a traditional FCM-based model for decision making in projects. [ABSTRACT FROM AUTHOR]

This paper presents application results of soft computing techniques in project's evaluation. The authors analyze different project management's guides regarding decision making techniques inside its. In this paper the authors combine traditional techniques for project's evaluation with soft computing techniques. The authors propose an algorithm that combine the following techniques: traditional indicators from project management guides, fuzzy inference systems, machine learning algorithms and linguistic data summarization methods. In section number 3, the paper presents the comparisons of algorithms Anfis, Hyfis, FS.HGD, based on neural networks with algorithms GFS LS RS, GFS THRIFT based on evolutionary algorithms. In experiments, we applied cross validation techniques combined with Friendman test and Wilcoxon test Afterwards, the authors present an algorithm that build linguistic summaries to detect causes of project management failures. Finally, we present a comparison of the results and the conclusions. [ABSTRACT FROM AUTHOR]