Abstract
Temporal abnormalities in events and gait phases of human walking can be potentially applied in the gait performance analysis. In this study is presented a novel real-time gait events detector that continuously considers the previous gait motions in order to improve this gait analysis. The detection of heel-strike and toe-off events is performed by a finite state machine (FSM), through decision rules and adaptive thresholds. The proposed algorithm stands out of the state-of-the-art by using adaptive thresholds in the FSM's decision rules, making the proposed gait event detector robust to sporadic perturbations, and adaptive to locomotion mode changes. For such, three stages were considered: thresholds' calibration, real-time detection of gait events and thresholds' update. Anatomical differences between lower limbs demanded independent FSMs for each limb. The algorithm was validated in a simulated biped model, and on a real DARwIn-OP robot, what shows up the generality of the proposed approach. Results highlight that the proposed algorithm correctly detects the gait events (accuracy of 100% and 84.348% in simulated and real conditions, respectively), with average time delays from 15.5 to 34ms. Thus, the proposed detector is an adaptive, accurate and versatile tool for real-time analysis of the feet movements along gait cycle.

Abstract
This paper describes a Hybrid User Centered Development Methodology (HUCDM). This is a simple, iterative and incremental development process that has as building blocks the principles of User Centered Design (UCD), specified in the International Organization for Standardization 9241-210. In its base lies the disciplined structure of development processes as well as practices and values from agile software development methods. The process consists of four main phases: planning, design, implementation and maintenance/operation. The prototyping and evaluation are carried out across the entire process. The HUCDM was implemented in an Educational Software Small and Medium Enterprise (SME) developer. The first feature based on this methodology was Courseware Sere. The quality of this educational resource has been internationally recognized. This Courseware was finalist in the national contest of multimedia products and thus got the interest of multinational companies such as BP - British Petroleum, which financed a new phase for the product development.

Abstract
Spatial Data Infrastructures (SDI) are repositories of large volumes of data, documented through standardized metadata. Data mining is one of the main techniques used to extract knowledge from large amounts of data, because of its versatility. The purpose of this article is to use clustering techniques and data mining to extract relationships and knowledge from metadata in SDI. For this reason, knowledge discovery techniques, clustering, text mining and data mining algorithms were used. In order to demonstrate the effectiveness of the proposed method, a case study was implemented to evaluate the performance of data mining techniques in this type of database. The results showed that the data mining process and clustering techniques guided to the classification proposed method for extracting relations and knowledge from a group of metadata extracted from within the database.

Abstract
The development of new technologies, information systems, decision support systems and clinical parameters prediction algorithms using machine learning and data mining opens a new perspective in many area of health. In this context, relevance presents the concept of Quality of Life (QOL) in health and the possibility of developing Support Systems Clinical Decision (SADC) that use it. Through individual expectation of physical well-being, psychological, mental, emotional and spiritual patients, discussed variables and measures the quality of research area of life, we intend to make a study of data to establish correlations with laboratory, pharmaceutical data, socio-economic, among others, obtaining knowledge in terms of behavioral patterns of chronic patients, achieving a number of reliable data and easily accessible, capable of enhancing the decision-making process by the specialized medical teams, seeking to improve treatments and consequently the related quality of life with the Health chronically ill. This paper studied and compared related studies that develop systems for decision support and prediction in the clinical area, with emphasis on studies in the area of quality of life.

Abstract
We investigate learning of flexible robot locomotion controllers, i.e., the controllers should be applicable for multiple contexts, for example different walking speeds, various slopes of the terrain or other physical properties of the robot. In our experiments, contexts are desired walking linear speed of the gait. Current approaches for learning control parameters of biped locomotion controllers are typically only applicable for a single context. They can be used for a particular context, for example to learn a gait with highest speed, lowest energy consumption or a combination of both. The question of our research is, how can we obtain a flexible walking controller that controls the robot (near) optimally for many different contexts? We achieve the desired flexibility of the controller by applying the recently developed contextual relative entropy policy search(REPS) method which generalizes the robot walking controller for different contexts, where a context is described by a real valued vector. In this paper we also extend the contextual REPS algorithm to learn a non-linear policy instead of a linear policy over the contexts which call it RBF-REPS as it uses Radial Basis Functions. In order to validate our method, we perform three simulation experiments including a walking experiment using a simulated NAO humanoid robot. The robot learns a policy to choose the controller parameters for a continuous set of forward walking speeds.

Abstract