http://hdl.handle.net/10366/131611 2026-04-23T05:00:50Z http://hdl.handle.net/10366/131647 This work presents a survivability prediction model for colon cancer developed with machine learning techniques. Survivability was viewed as a classification task where it was necessary to determine if a patient would survive each of the five years following treatment. The model was based on the SEER dataset which, after preprocessing, consisted of 38,592 records of colon cancer patients. Six features were extracted from a feature selection process in order to construct the model. This model was compared with another one with 18 features indicated by a physician. The results show that the performance of the six-feature model is close to that of the model using 18 features, which indicates that the first may be a good compromise between usability and performance. 2016-01-10T00:00:00Z http://hdl.handle.net/10366/131646 Artificial Intelligence (AI) methods contribute to the construction of systems where there is a need to automate the tasks. They are typically used for problems that have a large response time, or when a mathematical method cannot be used to solve the problem. However, the application of AI brings an added complexity to the development of such applications. AI has been frequently applied in the power systems field, namely in Electricity Markets (EM). In this area, AI applications are essentially used to forecast / estimate the prices of electricity or to search for the best opportunity to sell the product. This paper proposes a clustering methodology that is combined with fuzzy logic in order to perform the estimation of EM prices. The proposed method is based on the application of a clustering methodology that groups historic energy contracts according to their prices’ similarity. The optimal number of groups is automatically calculated taking into account the preference for the balance between the estimation error and the number of groups. The centroids of each cluster are used to define a dynamic fuzzy variable that approximates the tendency of contracts’ history. The resulting fuzzy variable allows estimating expected prices for contracts instantaneously and approximating missing values in the historic contracts. 2016-07-07T00:00:00Z http://hdl.handle.net/10366/131645 Family tree is an efficient data structure to store the kinship information in a family. There are basically two kinds of trees: Western Family Tree (WFT) and Oriental Family Tree such as Chinese Family Tree (CFT). To get an insight of their efficiency in the context of family kinship presentation and information extraction, in this paper we develop WFT and CFT presentation models and search algorithms, comparing their search performance and inherent mechanism. The study reveals that the computational cost is higher in CFT model, but it provides a greater gain in information retrieval and produces more details of the kinship between individuals in the family. 2016-01-10T00:00:00Z http://hdl.handle.net/10366/131644 In order to identify subjects in a convenient and efficient way one must use some special feature that makes it possible to discriminate between persons. Some of the features are biometric in nature, such as iris texture, hand shape, the human face, and of course finger prints. These play an important role in many automatic identification systems, since every person is believed to have a unique set of fingerprints. Before a fingerprint image can be looked up in a database, it has to be classified into one of 5 types in order to reduce processing times. 2016-01-10T00:00:00Z http://hdl.handle.net/10366/131643 2016-01-10T00:00:00Z http://hdl.handle.net/10366/131642 Last decade, biomedical and bioinformatics researchers have been demanding advanced and user-friendly applications for real use in practice. In this context, the Artificial Intelligence Workbench, an open-source Java desktop application framework for scientific software development, emerged with the goal of provid-ing support to both fundamental and applied research in the domain of transla-tional biomedicine and bioinformatics. AIBench automatically provides function-alities that are common to scientific applications, such as user parameter defini-tion, logging facilities, multi-threading execution, experiment repeatability, work-flow management, and fast user interface development, among others. Moreover, AIBench promotes a reusable component based architecture, which also allows assembling new applications by the reuse of libraries from existing projects or third-party software. Ten years have passed since the first release of AIBench, so it is time to look back and check if it has fulfilled the purposes for which it was conceived to and how it evolved over time. 2016-01-10T00:00:00Z http://hdl.handle.net/10366/131641 ABSTRACT/nThis article discusses the public administration strategy in the creation of electronic government (e-gov) Brazilian and interactivity of its population with this important way Shows trends and the consequences of its implementation, and the importance of its tools in disclosure and guidance to the population that public services and the relevance of the free software use as a government strategy. It also brings a reflection on the importance of transparency of government actions and commitment of resources of public administration. Also has the experience of São Paulo, in the urban transport sector in tires and the tools available to the user population. And it shows the valuable innovation to create Mobility Lab (MobLab), making the collaboration of the scientific community in city management.; /n  2016-01-10T00:00:00Z http://hdl.handle.net/10366/131640 The problem of face recognition has been extensively studied in the available literature, however, some aspects of this field require further research. The design and implementation of face recognition systems that can efficiently handle unconstrained conditions (e.g. pose variations, illumination, partial occlusion...) is still an area under active research. This work focuses on the design of a new nonparametric occlusion detection technique. In addition, we present some preliminary results that indicate that the proposed technique might be useful to face recognition systems, allowing them to dynamically discard occluded face parts. 2016-01-10T00:00:00Z http://hdl.handle.net/10366/131639 ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal, 2016, Vol. 5, N. 1, pp. I-II. 2016-01-10T00:00:00Z